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-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43339
    Prev
    Next
    INDEX
    Explanations

    the presence of initial tokens in a document, possibly indicating the start of different segments or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponses
    -0.77
     propOrder
    -0.64
    </tfoot>
    -0.59
    tanleria
    -0.58
     huéspedes
    -0.58
     Waray
    -0.57
     ExecuteAsync
    -0.57
    Santis
    -0.55
    Filmografia
    -0.55
     reminders
    -0.55
    POSITIVE LOGITS
     nahilalakip
    0.57
    WebVitals
    0.52
    expandindo
    0.51
     برانيه
    0.51
     pinulongan
    0.49
    numerusform
    0.48
     getopt
    0.47
     متعلقه
    0.46
    EndTag
    0.45
     Palme
    0.45
    Activations Density 0.236%

    No Known Activations