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. 1008
    Prev
    Next
    INDEX
    Explanations

    technical terms and numeric data related to accuracy, measurements, and tolerances

    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
    Viungo
    -0.55
     ProtoMessage
    -0.52
    apyrus
    -0.52
    }{*}{}
    -0.51
     mortgagee
    -0.48
    frank
    -0.48
     MainAxisSize
    -0.48
     vedo
    -0.47
    passage
    -0.47
    :][
    -0.47
    POSITIVE LOGITS
     accuracy
    0.94
     Accuracy
    0.92
    Accuracy
    0.89
     precisione
    0.83
     precision
    0.82
     précision
    0.78
     inaccuracy
    0.76
    accuracy
    0.76
     PRECISION
    0.75
    精度
    0.74
    Activations Density 1.149%

    No Known Activations