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. 17-GEMMASCOPE-RES-16K
    6. 10792
    Prev
    Next
    INDEX
    Explanations

    code elements related to error handling and status checking within software implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.57
    abestanden
    -0.53
     kaynağından
    -0.52
     Sling
    -0.50
     '@/
    -0.50
     pistas
    -0.50
     IDL
    -0.48
    بوابة
    -0.48
    KeyId
    -0.48
     fiches
    -0.46
    POSITIVE LOGITS
                                   
    0.75
    EndContext
    0.73
    chtenstein
    0.70
     ")");
    0.69
                    
    0.66
    Demografía
    0.63
    országban
    0.61
     Sert
    0.61
     detail
    0.60
    \{\\
    0.60
    Activations Density 0.095%

    No Known Activations