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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3126
    Prev
    Next
    INDEX
    Explanations

    cooking and baking instructions or ingredients related to recipes

    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
     فريبيس
    -0.73
     disambiguazione
    -0.64
    lably
    -0.59
     الحره
    -0.59
     itſelf
    -0.56
     pleaſure
    -0.52
     initComponents
    -0.52
    chengladbach
    -0.52
    addContainerGap
    -0.51
     THEOD
    -0.50
    POSITIVE LOGITS
    anneer
    0.61
    힣
    0.60
     cháy
    0.59
    ContentAlignment
    0.59
     onPostExecute
    0.58
    pexpr
    0.56
    ónima
    0.56
    Personendaten
    0.55
    URLException
    0.55
    getRuntime
    0.54
    Activations Density 0.113%

    No Known Activations