© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6930
    Prev
    Next
    INDEX
    Explanations

    references to variable names or symbols in code or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    computational or technical symbols and codes, particularly alphanumeric sequences and programming-related tokens.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    awaiter
    -0.52
    izon
    -0.51
     CEA
    -0.48
    VOA
    -0.48
    慨
    -0.47
    stahl
    -0.47
    FEA
    -0.47
    RTSC
    -0.47
     Fir
    -0.47
    $}}
    -0.47
    POSITIVE LOGITS
    k
    0.75
    kk
    0.68
    ambién
    0.66
    kkkk
    0.64
    ke
    0.64
    ky
    0.63
    ek
    0.62
    ck
    0.62
    𝘬
    0.61
    ik
    0.61
    Activations Density 0.769%

    No Known Activations