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. 68908
    Prev
    Next
    INDEX
    Explanations

    specific references to individuals and relationships

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

    proper names

    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
     kasarigan
    -1.01
     propOrder
    -0.98
    ConstraintMaker
    -0.95
    SourceChecksum
    -0.92
    astéroïdes
    -0.90
     ویکی‌پدی
    -0.87
    astéro
    -0.86
     poveznice
    -0.84
     linkovi
    -0.83
    省市镇
    -0.83
    POSITIVE LOGITS
    .
    0.41
    <h2>
    0.33
    3
    0.31
    4
    0.31
    1
    0.30
    2
    0.30
    K
    0.30
    9
    0.29
    8
    0.29
    。
    0.29
    Activations Density 0.007%

    No Known Activations