© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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
    6. 14203
    Prev
    Next
    INDEX
    Explanations

    JSON formatted strings or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
     NSCoder
    -0.90
    oneofs
    -0.66
     становника
    -0.63
     joaat
    -0.62
     صوتيه
    -0.62
    IVEREF
    -0.60
    ViewImports
    -0.59
    AsUp
    -0.58
     administrativos
    -0.57
    RUnlock
    -0.57
    POSITIVE LOGITS
    ({"
    0.95
    >{"
    0.92
    __["
    0.86
    ]["
    0.84
    ["
    0.81
    ({'
    0.80
     "{\"
    0.79
    ../../
    0.78
    gheny
    0.78
    <th>
    0.77
    Activations Density 0.074%

    No Known Activations