© 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. 27951
    Prev
    Next
    INDEX
    Explanations

    references to social gatherings and community events

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

    weekly and monthly meetings

    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
     nahilalakip
    -0.37
     ivelany
    -0.37
    ModelForm
    -0.33
     lulus
    -0.32
     kunde
    -0.32
    راتيج
    -0.32
    ScopeManager
    -0.31
     besten
    -0.31
     traiter
    -0.31
    Handlung
    -0.31
    POSITIVE LOGITS
     weekly
    0.90
    weekly
    0.78
     monthly
    0.76
    Weekly
    0.74
     semanal
    0.72
    Monthly
    0.69
    monthly
    0.68
     WEEKLY
    0.68
     Mondays
    0.67
     Tuesdays
    0.67
    Activations Density 0.014%

    No Known Activations