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. 24-GEMMASCOPE-RES-131K
    6. 893
    Prev
    Next
    INDEX
    Explanations

    references to genetic material and related biological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    DNA, mRNA, sound, plant, Senate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invokingState
    -0.79
    Viitteet
    -0.73
    transQ
    -0.71
     Autorizaciones
    -0.68
     فريبيس
    -0.65
    TagMode
    -0.63
     Réponses
    -0.62
     AssemblyCulture
    -0.62
    twimg
    -0.62
     nahilalakip
    -0.60
    POSITIVE LOGITS
    //
    0.40
     InputDecoration
    0.40
    styleUrls
    0.39
    __':
    
    0.34
     nonatomic
    0.32
    irl
    0.31
    BP
    0.30
    irn
    0.30
    keln
    0.29
    templateUrl
    0.28
    Activations Density 0.133%

    No Known Activations