© 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. 20-GEMMASCOPE-RES-16K
    11. 3294
    Prev
    Next
    INDEX
    Explanations

    phrases regarding legal or official statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to statements or documents, particularly in legal or technical contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    references to formal “statement(s)” in text, especially when paired with attribution, scope, or evaluative qualifiers (e.g., by/on/of, is true).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    bcrypt
    -0.48
    IBC
    -0.48
    honey
    -0.48
     כול
    -0.47
     IBC
    -0.46
    Computing
    -0.46
    Unemployment
    -0.46
    Honey
    -0.45
     Humber
    -0.45
    Oxy
    -0.44
    POSITIVE LOGITS
     statement
    1.14
     Statement
    1.05
     STATEMENT
    1.03
     statements
    0.98
    Statement
    0.95
     stmt
    0.93
    statement
    0.88
     Statements
    0.86
    STATEMENT
    0.84
     STATEMENTS
    0.82
    Activations Density 0.110%

    No Known Activations