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. 8-GEMMASCOPE-RES-16K
    6. 4637
    Prev
    Next
    INDEX
    Explanations

    code structure and function definitions within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaynağından
    -0.77
    Portale
    -0.73
     getItemCount
    -0.71
    fony
    -0.69
     Giordano
    -0.69
    GEBURTSDATUM
    -0.65
    istream
    -0.65
    modelBuilder
    -0.63
     tork
    -0.63
    setVerticalGroup
    -0.60
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.55
     delà
    0.54
    ---*/
    0.54
     lyon
    0.53
    EndContext
    0.53
    منابع
    0.50
     COLD
    0.50
    clone
    0.49
     Atas
    0.49
    PUTY
    0.49
    Activations Density 0.279%

    No Known Activations