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. 4-GEMMASCOPE-RES-16K
    6. 11073
    Prev
    Next
    INDEX
    Explanations

    function calls related to printing and input/output operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    model
    -0.66
    going
    -0.60
     gebruik
    -0.56
    Pen
    -0.55
    boo
    -0.53
    cons
    -0.53
     dàng
    -0.53
     model
    -0.53
    ური
    -0.53
    gin
    -0.52
    POSITIVE LOGITS
    printf
    2.62
     printf
    2.27
    Printf
    1.42
    stdio
    1.33
     AssemblyTitle
    1.26
     scanf
    1.25
    cstdio
    1.23
    scanf
    1.17
    Errorf
    1.15
    Sprintf
    1.14
    Activations Density 0.101%

    No Known Activations