Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2001
    Prev
    Next
    INDEX
    Explanations

    conditional statements in code, specifically those that begin with "else."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quiao
    -0.57
     ویکی‌پدی
    -0.52
    ()");
    -0.50
    };*/
    -0.50
    />";
    -0.49
    ‬‬
    -0.48
     strå
    -0.46
    cticut
    -0.45
    Voltaje
    -0.45
    //
    -0.45
    POSITIVE LOGITS
    else
    1.45
     else
    1.21
     ELSE
    1.05
     Else
    1.05
    Else
    0.98
    ELSE
    0.91
    elif
    0.85
     Otherwise
    0.83
    didSet
    0.77
    elseif
    0.77
    Activations Density 0.025%

    No Known Activations