© 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. 12699
    Prev
    Next
    INDEX
    Explanations

    terms related to automotive design and features

    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
     ModelExpression
    -0.63
     ProtoMessage
    -0.59
    addContainerGap
    -0.54
    endphp
    -0.53
     evidences
    -0.51
    OGND
    -0.51
    httphttps
    -0.50
    WriteLiteral
    -0.50
    ValueStyle
    -0.50
    FunctionFlags
    -0.49
    POSITIVE LOGITS
     recours
    0.53
     zufolge
    0.52
     ervan
    0.52
     insofar
    0.50
     sämtliche
    0.50
    全都
    0.50
     biçim
    0.50
     nonetheless
    0.49
     Owing
    0.47
    こうした
    0.47
    Activations Density 1.134%

    No Known Activations