© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 63491
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain formatting elements in legal or scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.86
    majánló
    -0.79
    DockStyle
    -0.79
    WithIOException
    -0.79
    CppMethod
    -0.78
    Бахар
    -0.77
    StructEnd
    -0.77
     tartalomajánló
    -0.76
     vooz
    -0.74
    InputBorder
    -0.74
    POSITIVE LOGITS
     Vork
    0.32
     Clearly
    0.31
    ↵↵
    0.31
    ).
    0.30
    .
    0.29
    Uns
    0.29
    кие
    0.29
    허
    0.29
     clearly
    0.29
    Clearly
    0.28
    Activations Density 0.018%

    No Known Activations