© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4605
    Prev
    Next
    INDEX
    Explanations

    specific terms related to food, cooking, and culinary experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.60
     كومونز
    -0.52
    oa̍t
    -0.46
     оригіналу
    -0.44
     للاسماء
    -0.42
    qrstuvwxyz
    -0.41
     Tariff
    -0.40
     ErrIntOverflow
    -0.39
     otomatig
    -0.39
    rzost
    -0.38
    POSITIVE LOGITS
     Te
    2.58
     te
    2.56
    Te
    2.38
     TE
    2.34
    TE
    1.96
    te
    1.90
     Те
    1.77
     tether
    1.73
     те
    1.73
     Té
    1.72
    Activations Density 2.252%

    No Known Activations