© 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. 1-GEMMASCOPE-RES-16K
    6. 12703
    Prev
    Next
    INDEX
    Explanations

    instances of counting or accounting actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.97
    "}>
    -0.78
    KommentareTeilen
    -0.74
    )».
    -0.73
    "]}
    -0.71
     initComponents
    -0.70
    .")]
    -0.69
    ?».
    -0.69
    "],
    
    -0.68
     }}">
    -0.66
    POSITIVE LOGITS
    Rüyada
    0.74
    <bos>
    0.52
    AsUp
    0.52
     plaît
    0.45
    Citiți
    0.44
    printStackTrace
    0.44
    เภ
    0.44
    Française
    0.43
    
    0.43
    inaudible
    0.42
    Activations Density 2.726%

    No Known Activations