Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9195
    Prev
    Next
    INDEX
    Explanations

    technical terms and code structure in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jegy
    -0.49
    بوابة
    -0.46
    Népesség
    -0.45
    cieux
    -0.45
    ̤
    -0.45
     titanic
    -0.44
     незавершена
    -0.43
    HAB
    -0.43
     majeur
    -0.42
     lhs
    -0.41
    POSITIVE LOGITS
    Hochspringen
    0.76
     intptr
    0.73
    wußt
    0.70
     مشين
    0.66
    SharedCtor
    0.66
    CompilerServices
    0.61
    Vanjske
    0.60
    WithIOException
    0.59
    Collegamenti
    0.59
    akaian
    0.58
    Activations Density 1.100%

    No Known Activations