© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6761
    Prev
    Next
    INDEX
    Explanations

    instances of control flow statements in code, particularly 'break' commands

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

    Code keyword "break" followed by semicolon

    np_acts-logits-general · gemini-2.0-flash

    break;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    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
     שוליים
    -0.56
    uarts
    -0.55
    PMailer
    -0.54
    '},
    -0.54
    ویر
    -0.54
    (\"
    -0.52
     isNameExpr
    -0.52
    &
    -0.52
     Normdatei
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.52
    break
    0.50
     endwhile
    0.48
    ContentAsync
    0.47
    EndContext
    0.43
    printStackTrace
    0.43
     <<<<<<<<<<<<<<
    0.41
    addGap
    0.40
    enterOuterAlt
    0.40
     burbujas
    0.39
    Activations Density 0.046%

    No Known Activations