© 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. 90578
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to systems, processes, and their interactions within various scientific and technical contexts

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

    abstract concepts or properties

    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
     فريبيس
    -0.68
     propOrder
    -0.62
     Italijanski
    -0.60
    UrlResolution
    -0.57
    MigrationBuilder
    -0.56
    uxxxx
    -0.54
    Бахар
    -0.51
    ")));
    
    -0.50
    '];
    
    -0.50
    '}),
    -0.49
    POSITIVE LOGITS
     miniaturka
    0.56
     gevoel
    0.54
     traseiro
    0.54
     oídos
    0.53
     leão
    0.49
     escritório
    0.48
     kapture
    0.48
     pulseras
    0.48
     namorado
    0.48
     gebied
    0.47
    Activations Density 0.180%

    No Known Activations