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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11193
    Prev
    Next
    INDEX
    Explanations

    method calls and function signatures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.57
     {},
    
    -0.46
    .";
    
    -0.46
     nessun
    -0.45
    IntOverflow
    -0.44
    webElementXpaths
    -0.44
     vPvB
    -0.44
     okuyayım
    -0.43
    )";
    
    -0.42
     cewek
    -0.42
    POSITIVE LOGITS
     GoogleFonts
    0.54
     bandeira
    0.49
     being
    0.47
     consultato
    0.47
    zarchiwizowane
    0.46
    óngase
    0.43
    ulemon
    0.43
    屋さん
    0.42
    reactstrap
    0.41
     appelez
    0.40
    Activations Density 0.079%

    No Known Activations