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. 35711
    Prev
    Next
    INDEX
    Explanations

    roles and activities related to involvement in organizations and contributions to leadership

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

    roles and affiliations

    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
    AddTagHelper
    -0.66
    ValueStyle
    -0.63
     enfans
    -0.57
    setVerticalGroup
    -0.57
    quelles
    -0.56
    ніципа
    -0.56
    parsedMessage
    -0.56
     moletom
    -0.55
    tvguidetime
    -0.55
    Према
    -0.55
    POSITIVE LOGITS
     many
    0.38
     several
    0.35
     FileReader
    0.33
    licken
    0.33
    many
    0.33
     other
    0.33
     pretty
    0.31
    </em>
    0.30
     array
    0.30
     CanadaChoose
    0.30
    Activations Density 0.012%

    No Known Activations