© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 56137
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structural elements in a document, such as brackets, special characters, or mathematical notation

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

    symbols and codes

    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
    OGND
    -1.27
    httphttps
    -1.13
     للاسماء
    -1.10
    afficheront
    -0.96
     betweenstory
    -0.95
     ब्रेकडाउन
    -0.93
    TagMode
    -0.91
    帖最后由
    -0.91
    UserScript
    -0.91
     مرئيه
    -0.90
    POSITIVE LOGITS
    2
    0.45
    ↵↵
    0.45
     contemporaine
    0.43
     parezca
    0.43
    The
    0.42
    This
    0.41
     Olsson
    0.41
     montanha
    0.41
    <strong>
    0.41
    All
    0.41
    Activations Density 0.013%

    No Known Activations