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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16278
    Prev
    Next
    INDEX
    Explanations

    items related to food and cooking equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.32
    Життєпис
    -0.29
     تعدى
    -0.28
     Chemin
    -0.28
    vateľ
    -0.27
     समीक्षाएं
    -0.27
    EditPart
    -0.26
     syphilis
    -0.26
    PONENTS
    -0.26
     trypto
    -0.26
    POSITIVE LOGITS
     ice
    2.16
     Ice
    1.88
    Ice
    1.79
     frozen
    1.76
     freezing
    1.67
     Frozen
    1.62
     freezer
    1.58
    冰
    1.56
     freeze
    1.55
    Frozen
    1.53
    Activations Density 0.238%

    No Known Activations