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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5219
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and data manipulation operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.56
    hyrchwyd
    -0.50
    SourceChecksum
    -0.47
     fat
    -0.39
    imagenes
    -0.39
    CppMethod
    -0.38
    鰭
    -0.37
     pros
    -0.37
     fast
    -0.36
    Enllaços
    -0.35
    POSITIVE LOGITS
     ویکی‌پدی
    0.55
    Према
    0.54
    SequentialGroup
    0.54
    enderror
    0.52
     AssemblyProduct
    0.52
    __(/*!
    0.49
    Fir
    0.47
     StatefulWidget
    0.46
     itſelf
    0.45
     endwhile
    0.44
    Activations Density 0.764%

    No Known Activations