Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7607
    Prev
    Next
    INDEX
    Explanations

    explicit descriptions of intimate or physical interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.65
    tvguidetime
    -0.54
     itſelf
    -0.54
    wiſe
    -0.52
     poffible
    -0.50
     autorytatywna
    -0.50
     poffe
    -0.49
     ſy
    -0.48
     ſel
    -0.48
    TypedDataSet
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.53
     مشين
    0.40
     dressing
    0.37
    setVerticalGroup
    0.37
    లాలు
    0.36
     onPostExecute
    0.36
    <?
    0.36
     stood
    0.35
    localctx
    0.35
    uação
    0.35
    Activations Density 0.349%

    No Known Activations