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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12671
    Prev
    Next
    INDEX
    Explanations

    references to figures and supplementary materials in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.51
    angliski
    -0.48
    queryInterface
    -0.48
     للاسماء
    -0.45
    antMatchers
    -0.45
    ViewById
    -0.44
    ConstraintMaker
    -0.44
    addGap
    -0.44
     ModelExpression
    -0.43
    Lähteet
    -0.42
    POSITIVE LOGITS
     shows
    0.72
     illustrates
    0.65
    rungsseite
    0.63
     intptr
    0.62
    shows
    0.61
     depicts
    0.59
    所示
    0.56
    Shows
    0.54
     demonstrates
    0.53
     Shows
    0.51
    Activations Density 0.908%

    No Known Activations