© 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. 99898
    Prev
    Next
    INDEX
    Explanations

    modal verbs and expressions of possibility or uncertainty

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

    modal verbs expressing possibility or condition

    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
     Freitas
    -0.63
    numerusform
    -0.59
     Popov
    -0.59
    躇
    -0.56
     Matos
    -0.55
     Infór
    -0.54
    тистика
    -0.53
     abstrato
    -0.53
    mbus
    -0.53
     Silber
    -0.52
    POSITIVE LOGITS
     consists
    0.45
    PreferredItem
    0.38
     revolves
    0.38
     doInBackground
    0.38
     consisted
    0.36
    IntoConstraints
    0.36
    setVerticalGroup
    0.35
    Hoje
    0.35
     rests
    0.34
     consist
    0.33
    Activations Density 0.029%

    No Known Activations