© 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. 976
    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
    dbc
    -0.73
     pinulongan
    -0.70
     McClellan
    -0.69
    owulf
    -0.67
    ciutto
    -0.67
    WriteLiteral
    -0.66
     gib
    -0.65
    ^^^
    -0.65
    abbix
    -0.65
    xions
    -0.64
    POSITIVE LOGITS
     year
    1.96
     YEAR
    1.67
     Year
    1.66
    year
    1.66
     years
    1.55
    Year
    1.55
    YEAR
    1.48
    years
    1.36
     Years
    1.27
    Years
    1.25
    Activations Density 0.078%

    No Known Activations