Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7977
    Prev
    Next
    INDEX
    Explanations

    statements related to responsibility and accountability in business or organizational contexts

    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
    WebVitals
    -0.81
    IsContent
    -0.77
    ynchronously
    -0.76
    تقاوى
    -0.75
     pinulongan
    -0.73
     snippetHide
    -0.72
     ExecuteAsync
    -0.71
    ViewImports
    -0.71
    Дереккөздер
    -0.69
    +#+#
    -0.69
    POSITIVE LOGITS
    UnknownFieldSet
    0.52
    arbeiten
    0.42
    auré
    0.41
     hands
    0.38
    ôi
    0.38
     butterknife
    0.38
    ối
    0.38
     roll
    0.36
    awtextra
    0.36
     мо
    0.36
    Activations Density 0.083%

    No Known Activations