© 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. 16-GEMMASCOPE-RES-16K
    11. 1324
    Prev
    Next
    INDEX
    Explanations

    references to seals and seal-related topics

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

    "Seal" followed by "hunting" or "Scholarship"

    np_acts-logits-general · gemini-2.0-flash

    seal hunting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.73
    aze
    -0.72
    i
    -0.69
    </blockquote>
    -0.67
    EDS
    -0.67
    Ingrid
    -0.66
    -0.66
     Shreveport
    -0.64
     Pute
    -0.64
    a
    -0.64
    POSITIVE LOGITS
     NAL
    0.98
     Leal
    0.94
     Kral
    0.94
     Ral
    0.94
     Gual
    0.93
    datal
    0.93
     LAL
    0.92
     Aal
    0.92
    ized
    0.92
    oredCriteria
    0.91
    Activations Density 0.375%
    No Known Activations