Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 150
    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
    ########.
    -0.86
    KommentareTeilen
    -0.84
    addCriterion
    -0.81
    StructEnd
    -0.79
    AddAttribute
    -0.75
    Demografie
    -0.69
    帖最后由
    -0.69
     Escort
    -0.68
    thâu
    -0.68
     gynhyrchwyd
    -0.68
    POSITIVE LOGITS
     javax
    2.27
    javax
    1.95
    avax
    0.80
     كومونز
    0.78
     Jax
    0.77
    ']?>
    0.75
     חיצוניים
    0.73
     getX
    0.71
     jax
    0.71
    Jax
    0.69
    Activations Density 0.003%

    No Known Activations