© 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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 1117
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -0.57
    .
    -0.55
    ).
    -0.53
     in
    -0.52
    LEncoder
    -0.49
     are
    -0.49
    </i>
    -0.49
    the
    -0.46
    2
    -0.46
     either
    -0.46
    POSITIVE LOGITS
    Parcelize
    0.93
     Paglinawan
    0.84
     كومونز
    0.77
     ویکی‌پدی
    0.76
    brainly
    0.76
     EconPapers
    0.73
     Efq
    0.71
    bootstrapcdn
    0.70
     للمعارف
    0.69
    енча
    0.69
    Activations Density 0.204%

    No Known Activations