© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101528
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formulae involving parentheses and embedded symbols

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

    closing parenthesis symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    <bos>
    -0.94
    Tikang
    -0.65
    WriteBarrier
    -0.60
    uxxxx
    -0.60
     Италијани
    -0.60
    afficheront
    -0.57
    erobic
    -0.57
     CanadaChoose
    -0.56
    Kirch
    -0.54
    latin
    -0.54
    POSITIVE LOGITS
    )))))
    0.67
    )..
    0.65
    )))
    0.65
    (")");
    0.63
    ))))
    0.63
    ))),
    0.60
    )).
    0.59
    ))
    0.59
    ))).
    0.59
    ))))))))
    0.58
    Activations Density 0.173%

    No Known Activations