© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8972
    Prev
    Next
    INDEX
    Explanations

    sports statistics and performance metrics

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

    offense and defense

    np_acts-logits-general · gemini-2.0-flash

    offense defense stats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RunAsync
    -0.55
    splatz
    -0.53
     pré
    -0.47
    ManagedBean
    -0.45
    multirow
    -0.45
     deltag
    -0.45
    DebuggerNonUser
    -0.45
    ліст
    -0.44
    HAP
    -0.42
    rxjs
    -0.41
    POSITIVE LOGITS
     defense
    0.92
     offense
    0.84
     offensively
    0.81
     defensively
    0.80
     defence
    0.79
    defense
    0.76
     defensive
    0.75
    uxxxx
    0.74
     betweenstory
    0.73
     scoring
    0.72
    Activations Density 0.139%

    No Known Activations