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. 43
    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
     Haitian
    -0.82
    tableFuture
    -0.79
     Erb
    -0.78
     figliu
    -0.77
    ).]
    -0.77
    (".");
    -0.75
     Yol
    -0.73
    },[])
    -0.73
    setOnAction
    -0.73
    ="<?=$
    -0.72
    POSITIVE LOGITS
     Sw
    1.51
    Sw
    1.42
     SW
    1.35
     Swain
    1.31
     sw
    1.25
    sw
    1.25
    SW
    1.16
     Swans
    1.16
     Swanson
    1.13
     Swartz
    1.09
    Activations Density 0.034%

    No Known Activations