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. 10188
    Prev
    Next
    INDEX
    Explanations

    references to infrastructure and related projects

    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
     AppBundle
    -0.86
     Trin
    -0.80
     Fielding
    -0.80
     clazz
    -0.79
     Beatrix
    -0.78
     Minaj
    -0.77
     CommandType
    -0.77
    Cubit
    -0.77
    FloatField
    -0.77
    endpush
    -0.76
    POSITIVE LOGITS
     Vau
    1.00
    textbf
    0.79
    custo
    0.78
     Numa
    0.74
    thentic
    0.71
    wau
    0.69
     ALO
    0.69
    tocin
    0.67
    — 
    0.66
     Dore
    0.64
    Activations Density 0.359%

    No Known Activations