© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4626
    Prev
    Next
    INDEX
    Explanations

    effective methods and approaches to achieve various goals

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

    "...way of..." or "...methods for..."

    np_acts-logits-general · gemini-2.0-flash

    way of

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    agoza
    -0.45
     ModelExpression
    -0.41
    PerformLayout
    -0.41
    AuthContext
    -0.41
    endfor
    -0.40
    
    -0.38
    QtGui
    -0.37
     Regist
    -0.37
     createdBy
    -0.36
     createContext
    -0.36
    POSITIVE LOGITS
    bootstrapcdn
    0.56
     moyen
    0.53
     solution
    0.52
    solution
    0.50
     strategy
    0.50
     façon
    0.47
    providedIn
    0.47
     approach
    0.47
    aarrggbb
    0.47
     method
    0.46
    Activations Density 0.401%

    No Known Activations