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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6107
    Prev
    Next
    INDEX
    Explanations

    the presence of less than characters or similar syntax elements in the context of programming code

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

    "for (i = 0; i <" code loops

    np_acts-logits-general · gemini-2.0-flash

    for loop structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.86
    fromnode
    -0.67
    MigrationBuilder
    -0.66
    sizeCache
    -0.63
     ویکی‌پدیا
    -0.59
    AutoScaleMode
    -0.58
    
    -0.58
     AssemblyCulture
    -0.58
     surla
    -0.57
    
    -0.57
    POSITIVE LOGITS
     the
    0.35
     règne
    0.35
     penerbangan
    0.33
    entraînement
    0.33
     surtido
    0.33
    ProgressHUD
    0.33
    forhold
    0.32
     dignité
    0.32
     nearly
    0.31
    untung
    0.31
    Activations Density 0.125%

    No Known Activations