© 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. 79267
    Prev
    Next
    INDEX
    Explanations

    references to file operations and data handling in programming contexts

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

    file paths and names

    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
     AssemblyCulture
    -0.76
    
    -0.60
    RefNanny
    -0.59
    IntoConstraints
    -0.56
    AddTagHelper
    -0.56
     CURIAM
    -0.56
    setVerticalGroup
    -0.54
     StatelessWidget
    -0.52
    RuleContext
    -0.52
     ujednoznacz
    -0.52
    POSITIVE LOGITS
     Einfluß
    0.49
     Aufenthalts
    0.46
     Vorbild
    0.44
     ziyaret
    0.43
    ícone
    0.41
     Verhält
    0.41
     Inhalt
    0.41
    msgTypes
    0.40
     contents
    0.40
     selatan
    0.40
    Activations Density 0.012%

    No Known Activations