© 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. 112167
    Prev
    Next
    INDEX
    Explanations

    remarks about performance and opportunity in sports contexts

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

    common sentence starters

    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
     embaj
    -0.49
     EconPapers
    -0.46
     desierto
    -0.46
     guía
    -0.45
    VIAF
    -0.44
     partecip
    -0.44
     gobern
    -0.44
     jueces
    -0.44
     obispo
    -0.43
    ControllerAdvice
    -0.42
    POSITIVE LOGITS
    principalColumn
    0.44
    OpenHelper
    0.42
    __(/*!
    0.40
     الحره
    0.40
    IsMutable
    0.39
     Swag
    0.37
    pDialog
    0.37
    ebra
    0.37
    awaiter
    0.36
     slowing
    0.35
    Activations Density 0.044%

    No Known Activations