© 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. 12-GEMMASCOPE-RES-16K
    11. 3825
    Prev
    Next
    INDEX
    Explanations

    phrases that express negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.67
     فريبيس
    -0.62
    Personendaten
    -0.52
    */),
    -0.52
    fxml
    -0.48
     otomatig
    -0.47
    ,:);
    -0.47
     AssemblyCulture
    -0.46
    copg
    -0.46
    GTCX
    -0.46
    POSITIVE LOGITS
     nothing
    0.77
     NOTHING
    0.74
    全く
    0.74
    まったく
    0.72
    Nothing
    0.71
     none
    0.71
     Nothing
    0.70
     никакого
    0.69
    nothing
    0.68
    何も
    0.66
    Activations Density 0.829%

    No Known Activations