© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 4636
    Prev
    Next
    INDEX
    Explanations

    references to specific motorsport entries and drivers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.83
     صوتيه
    -0.76
     BoxDecoration
    -0.66
    !("{}",
    -0.62
    ChildScrollView
    -0.57
    ollectionView
    -0.57
    cshtml
    -0.55
    UpInside
    -0.53
     beliebt
    -0.53
    Datuak
    -0.52
    POSITIVE LOGITS
     team
    1.03
    team
    0.94
     Team
    0.88
    Team
    0.87
     teams
    0.80
    TEAM
    0.73
     TEAM
    0.72
    teams
    0.72
    InjectAttribute
    0.67
     Mannschaft
    0.67
    Activations Density 0.098%

    No Known Activations