© 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. 1-GEMMASCOPE-RES-16K
    11. 2344
    Prev
    Next
    INDEX
    Explanations

    complex ideas involving analysis and exploration of various structures and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonode
    -0.44
    queryInterface
    -0.36
    ValueStyle
    -0.35
     autorytatywna
    -0.35
    writeFieldEnd
    -0.35
     piłkarz
    -0.34
    SharedCtor
    -0.33
     she
    -0.33
     its
    -0.32
    TokenNameLBRACE
    -0.31
    POSITIVE LOGITS
    MigrationBuilder
    0.53
     především
    0.47
     redacción
    0.46
    ＊＊＊
    0.43
     Etc
    0.43
    XtraReports
    0.42
     seguente
    0.42
     BytesLike
    0.41
    AndSet
    0.41
    Glej
    0.41
    Activations Density 1.630%

    No Known Activations