© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13215
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between entities and concepts, particularly in the context of requirements and qualifications in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    relational phrases that connect entities or concepts with prepositions like "with," "to," or "and."

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    phrases indicating relationships or associations between two entities or concepts, typically using prepositions like "to" and "with".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases expressing relationships or associations between entities, typically linking one thing to/with another.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.58
    UnusedPrivate
    -0.56
     StatefulWidget
    -0.55
    WebpackPlugin
    -0.53
    AndEndTag
    -0.52
     AssemblyCompany
    -0.52
    ſelves
    -0.51
    ftagPool
    -0.51
    moveToFirst
    -0.51
    SharedDtor
    -0.50
    POSITIVE LOGITS
     varandra
    0.66
     itself
    0.63
     nhau
    0.58
     eachother
    0.57
     existing
    0.56
     other
    0.55
     reality
    0.52
     собой
    0.47
     realities
    0.46
     altrett
    0.45
    Activations Density 1.239%

    No Known Activations