© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10167
    Prev
    Next
    INDEX
    Explanations

    elements related to the interactions and relationships between words in a written context

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

    words describing how language elements interact, combine, or relate to each other.

    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
    ThroughAttribute
    -0.42
    postsleuth
    -0.38
    @",
    -0.37
     autorytatywna
    -0.36
    SpringBootTest
    -0.35
     snippetHide
    -0.34
     köpa
    -0.33
     Muslims
    -0.33
     ndani
    -0.33
     Humans
    -0.32
    POSITIVE LOGITS
    AndEndTag
    0.60
     naughty
    0.59
    dance
    0.57
     oprot
    0.57
     bará
    0.55
     dances
    0.54
     kissed
    0.54
    naughty
    0.54
    optionalTypeArgs
    0.54
    behaved
    0.53
    Activations Density 0.420%

    No Known Activations