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. 8467
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries about knowledge and information

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

    want to know

    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
    ientras
    -0.75
    ágenes
    -0.65
     GoogleFonts
    -0.65
    ambién
    -0.58
    })*/
    -0.57
    ugeot
    -0.57
     Geſ
    -0.56
    guiente
    -0.56
    )"),
    -0.56
     ainfi
    -0.56
    POSITIVE LOGITS
    想知道
    0.65
     know
    0.63
     KNOW
    0.56
     how
    0.56
    Know
    0.56
     узнать
    0.55
     Know
    0.55
    Knows
    0.50
     wissen
    0.50
     information
    0.49
    Activations Density 0.014%

    No Known Activations