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. 15494
    Prev
    Next
    INDEX
    Explanations

    programming constructs and variable assignments

    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
     kasarigan
    -0.76
     desmotivaciones
    -0.69
    pecabe
    -0.68
     Komunikasi
    -0.66
     Infór
    -0.64
     Majefty
    -0.63
     Anſ
    -0.63
     ainfi
    -0.62
     valentín
    -0.61
     Geſ
    -0.60
    POSITIVE LOGITS
     c
    0.38
     is
    0.36
     ster
    0.35
     itself
    0.33
     here
    0.33
     h
    0.33
     said
    0.32
     herself
    0.32
     pri
    0.31
     para
    0.31
    Activations Density 0.112%

    No Known Activations