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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 1838
    Prev
    Next
    INDEX
    Explanations

    occurrences of the `printf` function within C programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    -0.67
    rel
    -0.64
     Star
    -0.63
    end
    -0.63
    4
    -0.61
    endregion
    -0.61
     Dro
    -0.61
     Meta
    -0.60
     Drop
    -0.60
    cons
    -0.60
    POSITIVE LOGITS
    stdio
    1.60
     printf
    1.39
    printf
    1.39
    cstdio
    1.29
     scanf
    1.27
     AssemblyTitle
    1.12
    WithFormat
    1.11
    scanf
    1.06
    obbies
    0.92
    Errorf
    0.90
    Activations Density 0.036%

    No Known Activations