© 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. 22-GEMMASCOPE-RES-16K
    6. 15348
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting and structure in documents

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

    Content within LaTeX math environments

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -2.26
     myſelf
    -2.13
     itſelf
    -2.02
     Theſe
    -1.95
    ſelf
    -1.88
     doubtnut
    -1.86
     ſeveral
    -1.85
     Majefty
    -1.83
     Monfieur
    -1.82
     Jefus
    -1.81
    POSITIVE LOGITS
     
    0.97
    .
    0.86
      
    0.86
     (
    0.84
    ↵
    0.81
    ,
    0.81
    </strong>
    0.77
    '
    0.75
    …
    0.74
     -
    0.73
    Activations Density 1.081%

    No Known Activations