Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 51879
    Prev
    Next
    INDEX
    Explanations

    key details related to events and academic gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    MessageTagHelper
    -0.41
     ब्रेकडाउन
    -0.38
    vician
    -0.37
    TypedDataSet
    -0.36
     getItemCount
    -0.36
     flexibilidad
    -0.34
     AttributeSet
    -0.34
    eddable
    -0.34
     existencia
    -0.33
     vorhandenen
    -0.33
    POSITIVE LOGITS
     debate
    0.63
     conference
    0.63
     seminar
    0.60
     deliber
    0.60
     convened
    0.59
     Veranstaltung
    0.59
     symposium
    0.57
     discussing
    0.55
     discussions
    0.55
     webinar
    0.55
    Activations Density 0.013%

    No Known Activations