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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6667
    Prev
    Next
    INDEX
    Explanations

    references to strength or potency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitVars
    -0.50
    JsonPropertyName
    -0.49
     useAppContext
    -0.48
     uVar
    -0.48
    GraphicsUnit
    -0.48
    Tembelea
    -0.48
    liday
    -0.47
    CPtr
    -0.47
     '{@
    -0.46
    MigrationBuilder
    -0.46
    POSITIVE LOGITS
     strong
    2.19
    strong
    2.11
    Strong
    2.03
     Strong
    2.02
     STRONG
    1.91
    STRONG
    1.80
     strongly
    1.66
    strongly
    1.58
     stronger
    1.52
     strongest
    1.48
    Activations Density 0.133%

    No Known Activations