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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 38-GEMMASCOPE-RES-16K
    6. 10288
    Prev
    Next
    INDEX
    Explanations

    elements of code related to function definitions and method calls in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptonshire
    -0.49
    FieldBuilder
    -0.47
    PostBack
    -0.44
    ineri
    -0.44
    InitVars
    -0.42
    GEBURTSDATUM
    -0.42
     Spreading
    -0.41
     Anlass
    -0.39
     spreading
    -0.39
     Spread
    -0.39
    POSITIVE LOGITS
     NS
    0.85
     iPhone
    0.81
     Apple
    0.76
    iPhone
    0.75
     iOS
    0.74
     apple
    0.71
    Apple
    0.70
     iPad
    0.70
     iPhones
    0.68
     iphone
    0.68
    Activations Density 0.863%

    No Known Activations