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

    Neuronpedia

    Jacobian LensNEW
    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. 14782
    Prev
    Next
    INDEX
    Explanations

    occurrences of system output statements and Java-related code structures

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

    Code snippets with "System" or "Math"

    np_acts-logits-general · gemini-2.0-flash

    code identifiers, system calls

    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
    ,
    -0.56
     Schulte
    -0.52
     Backman
    -0.50
    พาะ
    -0.41
     Ried
    -0.40
    ;
    -0.40
    /
    -0.40
     Krzyż
    -0.39
     Kruse
    -0.39
     Dowling
    -0.39
    POSITIVE LOGITS
     FontWeight
    1.03
     GenerationType
    0.82
    GroupLayout
    0.75
    LEncoder
    0.73
    redients
    0.73
     ſei
    0.73
     rowspan
    0.71
     الاطلاع
    0.71
    hematical
    0.70
    tagHelperRunner
    0.69
    Activations Density 0.142%

    No Known Activations