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. 65968
    Prev
    Next
    INDEX
    Explanations

    structural dimensions and specifications, particularly related to buildings or landmarks

    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
     nahilalakip
    -0.75
     للاسماء
    -0.74
    InputBorder
    -0.73
     مشين
    -0.70
    ----</
    -0.69
    CloseOperation
    -0.68
     AssemblyCulture
    -0.68
    GEBURTSDATUM
    -0.67
     nonUne
    -0.67
    ########.
    -0.66
    POSITIVE LOGITS
     thirty
    0.69
     twenty
    0.65
    Twenty
    0.64
     forty
    0.63
     Twenty
    0.61
    Thirty
    0.59
     sixty
    0.59
     Thirty
    0.57
    twenty
    0.56
    二十
    0.55
    Activations Density 0.026%

    No Known Activations