© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12001
    Prev
    Next
    INDEX
    Explanations

    technical language and structured elements related to programming or data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.88
    +#+#
    -0.84
    tagHelperRunner
    -0.63
    IndentedString
    -0.60
    rrggbb
    -0.58
    FunctionFlags
    -0.58
    GeoNames
    -0.57
    ništ
    -0.57
    WritableDatabase
    -0.55
    bootstrapcdn
    -0.55
    POSITIVE LOGITS
    asztal
    0.54
    getLog
    0.52
    \{\\
    0.51
    csolódó
    0.51
    UnknownFields
    0.50
    viewDid
    0.50
    Ensuite
    0.49
    elte
    0.49
    dibly
    0.48
     aria
    0.47
    Activations Density 1.344%

    No Known Activations