Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 46056
    Prev
    Next
    INDEX
    Explanations

    structural elements commonly used in data tables or spreadsheets

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

    parenthesized numbers

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Personendaten
    -1.05
     queſta
    -0.97
     $_(
    -0.94
    ſſung
    -0.91
    ロウィン
    -0.89
     فريبيس
    -0.88
    bootstrapcdn
    -0.88
     autorytatywna
    -0.87
     ſind
    -0.87
    <unused3>
    -0.86
    POSITIVE LOGITS
    ↵↵
    0.76
    .
    0.65
    ↵↵↵
    0.55
    ↵↵↵↵
    0.53
    ↵
    0.51
    。
    0.48
    1
    0.46
    ).
    0.45
    2
    0.45
    );
    0.45
    Activations Density 0.006%

    No Known Activations