© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 54212
    Prev
    Next
    INDEX
    Explanations

    bullet points or list-like structures within the text

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

    bullet points and symbols

    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
    expandindo
    -0.91
     autorytatywna
    -0.78
    WireFormatLite
    -0.76
    يكب
    -0.75
    AndEndTag
    -0.71
     चीज़ों
    -0.71
    хьтан
    -0.71
    CloseOperation
    -0.71
     الحره
    -0.70
    OGND
    -0.69
    POSITIVE LOGITS
    The
    0.74
     The
    0.65
    A
    0.54
    In
    0.50
     A
    0.50
    When
    0.48
    By
    0.47
    For
    0.47
    After
    0.47
    From
    0.47
    Activations Density 0.045%

    No Known Activations