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
    6. 1077
    Prev
    Next
    INDEX
    Explanations

    the absence of significant content or meaningful information

    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
     esmeralda
    -0.78
     Legendre
    -0.77
     Belk
    -0.76
     Kuba
    -0.76
     dorada
    -0.73
     PRD
    -0.72
     TableColumn
    -0.70
     cuillère
    -0.70
     Athen
    -0.69
     Hildebrand
    -0.69
    POSITIVE LOGITS
     Not
    1.07
    Not
    0.98
     not
    0.96
     quite
    0.95
     NOT
    0.90
    Quite
    0.90
     Quite
    0.89
    not
    0.80
     really
    0.79
    NOT
    0.76
    Activations Density 0.090%

    No Known Activations