© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3775
    Prev
    Next
    INDEX
    Explanations

    keywords and syntax used for control flow statements in programming

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

    programming code structures, particularly control flow statements like if-else and code blocks marked by curly braces {}.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    alternative branches in conditional logic (the else/otherwise part of if statements) in code.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    closing braces or brackets that end conditional blocks (if/else statements) in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    
    -0.79
     ब्रेकडाउन
    -0.77
    addPreferredGap
    -0.77
     defaultstate
    -0.77
    bitField
    -0.74
    InputBorder
    -0.73
    Obrázky
    -0.72
    Tikang
    -0.70
    MigrationBuilder
    -0.69
     NSCoder
    -0.69
    POSITIVE LOGITS
    ERVIS
    0.32
    Writer
    0.29
    ากาศ
    0.29
    直接
    0.29
    多
    0.29
    A
    0.28
    别
    0.28
    The
    0.28
     A
    0.28
    tadır
    0.28
    Activations Density 0.093%

    No Known Activations