© 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. 20-GEMMASCOPE-RES-16K
    11. 1448
    Prev
    Next
    INDEX
    Explanations

    elements related to database operations and file handling in code

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

    File paths or names

    np_acts-logits-general · gemini-2.0-flash

    file path naming and processing

    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
     Administrativna
    -0.69
     ویکی‌پدی
    -0.51
     autorytatywna
    -0.47
    tagHelperRunner
    -0.42
    HideFlags
    -0.39
     لينك
    -0.38
    quoise
    -0.36
     Мексичка
    -0.36
    ywna
    -0.35
     fratelli
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.53
    argout
    0.44
    resave
    0.42
    Erstellt
    0.42
     output
    0.41
    Résultats
    0.41
     inplace
    0.40
    存于互联网档案馆
    0.40
     ModelExpression
    0.40
     通販
    0.39
    Activations Density 0.566%

    No Known Activations