© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3495
    Prev
    Next
    INDEX
    Explanations

    words indicating capability or function

    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
    ">//
    -1.05
    providedIn
    -0.85
    
    -0.75
     विश्वसनीयता
    -0.72
     ModelExpression
    -0.71
    出版年
    -0.70
    ||||
    -0.69
    帖最后由
    -0.69
    évaluateur
    -0.69
    CodeAttribute
    -0.68
    POSITIVE LOGITS
     receipt
    0.83
    )_{
    0.73
    receipt
    0.71
     Com
    0.70
    sp
    0.68
     Receipt
    0.67
    Ca
    0.66
     Ca
    0.65
     capable
    0.65
    capable
    0.61
    Activations Density 0.080%

    No Known Activations