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. 23-GEMMASCOPE-RES-131K
    6. 77
    Prev
    Next
    INDEX
    Explanations

    terms associated with vegan and vegetarian dietary options

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wirkung
    -0.48
    adpleegd
    -0.47
    CloseOperation
    -0.45
     Meldung
    -0.44
     للاسماء
    -0.43
    ordeel
    -0.41
    houding
    -0.41
    CommandText
    -0.41
     productivo
    -0.41
     efficacité
    -0.41
    POSITIVE LOGITS
    MessageTagHelper
    0.57
     الرياضيه
    0.55
    #
    0.53
    /**
    0.50
     endfor
    0.49
    //
    0.49
     saites
    0.47
     Parcelable
    0.46
    ftagPool
    0.46
     kran
    0.45
    Activations Density 0.017%

    No Known Activations