© 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. 2530
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connections between ideas and information

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

    the word "and" used to connect items in lists or series of related concepts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     pères
    -0.53
     âmes
    -0.47
     yeux
    -0.45
     gouvernements
    -0.45
     Dunn
    -0.44
     lèvres
    -0.44
     médecins
    -0.42
     Kim
    -0.40
    SourceChecksum
    -0.40
     sièges
    -0.38
    POSITIVE LOGITS
    SharedDtor
    0.65
    acies
    0.63
     gadgets
    0.63
     rituals
    0.62
     slogans
    0.62
     impulses
    0.61
     potentials
    0.61
     traditions
    0.59
     potentialities
    0.59
     conveniences
    0.59
    Activations Density 0.488%

    No Known Activations