© 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. 93215
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and references to variables in equations

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

    math operator \rm followed by E or tr

    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
    новниш
    -0.65
    Tikang
    -0.64
    RenderAtEndOf
    -0.63
    Personendaten
    -0.63
    lusconi
    -0.63
    makeConstraints
    -0.62
    devamını
    -0.62
     Infór
    -0.61
    ⅘
    -0.60
    Rüyada
    -0.59
    POSITIVE LOGITS
     mathvariant
    0.68
    mathbf
    0.40
     Ph
    0.39
    normal
    0.38
    <0xEA>
    0.38
    <b>
    0.37
    mtext
    0.36
    MainThread
    0.35
     Vargas
    0.35
    NonNull
    0.34
    Activations Density 0.012%

    No Known Activations