© 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. 8444
    Prev
    Next
    INDEX
    Explanations

    symbols and structural elements commonly found in mathematical or scientific expressions

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

    "W" followed by another letter

    np_acts-logits-general · gemini-2.0-flash

    words starting with W

    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
    ISupport
    -0.52
    cury
    -0.44
    principalTable
    -0.43
     $__
    -0.43
    noons
    -0.42
    று
    -0.41
    $__
    -0.41
     समीक्षाओं
    -0.40
     pháp
    -0.40
     Gruy
    -0.40
    POSITIVE LOGITS
    W
    0.99
     W
    0.97
    w
    0.95
     w
    0.90
    weight
    0.88
     weight
    0.86
    WD
    0.86
    Weight
    0.86
     watt
    0.85
    wpi
    0.85
    Activations Density 0.474%

    No Known Activations