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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14719
    Prev
    Next
    INDEX
    Explanations

    function calls and return statements in programming code

    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
    CloseOperation
    -0.96
     propOrder
    -0.95
    webElementXpaths
    -0.93
    RTEX
    -0.90
    findpost
    -0.85
     שוליים
    -0.81
     Normdatei
    -0.81
    CppMethod
    -0.80
    ConstraintMaker
    -0.77
     يتيمه
    -0.77
    POSITIVE LOGITS
    ↵↵
    0.45
    return
    0.40
    <eos>
    0.38
    .
    0.36
    ..
    0.35
     «
    0.33
    ↵
    0.31
     rather
    0.31
    ToReturn
    0.30
    。
    0.30
    Activations Density 0.559%

    No Known Activations