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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14535
    Prev
    Next
    INDEX
    Explanations

    specific statistics and performance metrics related to sports events

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

    Statistics about wins, losses, and scores

    np_acts-logits-general · gemini-2.0-flash

    winning streaks and scores

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    InitVars
    -0.65
    GenerationType
    -0.65
    ScopeManager
    -0.57
    ChildScrollView
    -0.56
     hochzeit
    -0.56
    InjectAttribute
    -0.55
    principalTable
    -0.54
     ब्रेकडाउन
    -0.52
    rašymas
    -0.52
    AutoScaleMode
    -0.51
    POSITIVE LOGITS
     almost
    0.37
    殆
    0.33
     close
    0.33
     virtually
    0.33
     aproape
    0.32
     quase
    0.31
     hardly
    0.30
    almost
    0.28
     seven
    0.28
     failed
    0.28
    Activations Density 0.209%

    No Known Activations