Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 90292
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or entities related to controversial topics

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

    user interaction

    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
    ftagPool
    -0.62
    ConstraintMaker
    -0.60
    
    -0.54
     препратки
    -0.52
    fromCharCode
    -0.51
    IntoConstraints
    -0.50
    锈钢
    -0.50
     iNdEx
    -0.49
     CreateTagHelper
    -0.48
     BorderSide
    -0.48
    POSITIVE LOGITS
    Focus
    0.35
     nargin
    0.35
     Geraadpleegd
    0.34
     âgées
    0.34
     viaj
    0.33
    Kraj
    0.33
     userEmail
    0.33
     Hentet
    0.32
    fahr
    0.32
    usions
    0.31
    Activations Density 0.000%

    No Known Activations