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 - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65850
    Prev
    Next
    INDEX
    Explanations

    actions or processes relating to food preparation or cooking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SwitchCompat
    -0.51
    Географиясе
    -0.50
    lwjgl
    -0.49
    InstrumentedTest
    -0.47
    IBarButtonItem
    -0.46
    rrggbb
    -0.46
    endpush
    -0.46
    /******/
    -0.46
    InlineData
    -0.46
    UIControlState
    -0.46
    POSITIVE LOGITS
     limpio
    0.62
     pulito
    0.62
     terpisah
    0.60
     samostat
    0.48
     preparada
    0.47
     prepared
    0.47
     another
    0.47
     preparado
    0.46
     center
    0.46
    乾淨
    0.46
    Activations Density 0.033%

    No Known Activations