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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7490
    Prev
    Next
    INDEX
    Explanations

    function return types and promises in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kaya
    -0.53
     ग्राहक
    -0.52
    Clk
    -0.47
    ising
    -0.46
     seconda
    -0.42
     arose
    -0.42
     writeTo
    -0.41
    endencies
    -0.41
    ova
    -0.40
     limba
    -0.40
    POSITIVE LOGITS
    IsContent
    1.05
     Returns
    0.92
    tableFuture
    0.90
     مرئيه
    0.88
    migrationBuilder
    0.84
    Returns
    0.83
     returns
    0.81
    DebuggerNonUser
    0.80
    Geplaatst
    0.79
     RETURN
    0.77
    Activations Density 0.159%

    No Known Activations