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. 19-GEMMASCOPE-RES-16K
    6. 334
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax related to variable declarations and function definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.55
     considérons
    -0.52
     كورة
    -0.51
    korb
    -0.51
    тистика
    -0.50
    setcounter
    -0.49
     оригіналу
    -0.49
    InputTagHelper
    -0.48
     Batista
    -0.48
     مرئيه
    -0.48
    POSITIVE LOGITS
     string
    1.94
     String
    1.90
    String
    1.83
    string
    1.72
     strings
    1.66
    字符串
    1.57
    NSString
    1.54
     Strings
    1.51
     str
    1.46
    STRING
    1.41
    Activations Density 0.892%

    No Known Activations