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. 6013
    Prev
    Next
    INDEX
    Explanations

    references to functions in programming contexts

    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
     erwartet
    -0.40
    malige
    -0.39
    daje
    -0.37
     Mejía
    -0.37
    Overlay
    -0.36
     teuer
    -0.35
     leichte
    -0.35
     earliest
    -0.35
    cached
    -0.34
     glaubt
    -0.34
    POSITIVE LOGITS
     Function
    1.29
    function
    1.20
     function
    1.18
    Function
    1.17
     Functions
    1.12
     Func
    1.08
     FUNCTION
    1.08
    FunctionType
    1.06
     functions
    1.05
    FUNCTION
    1.05
    Activations Density 0.141%

    No Known Activations