© 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. 35-GEMMASCOPE-RES-16K
    11. 12458
    Prev
    Next
    INDEX
    Explanations

    code-related terms, especially those related to function definitions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    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
    -0.34
     both
    -0.32
     createSprite
    -0.28
    else
    -0.28
     عنه
    -0.27
     into
    -0.26
    化为
    -0.26
    偏偏
    -0.26
     Aussicht
    -0.26
    Both
    -0.26
    POSITIVE LOGITS
     counter
    1.03
     counters
    0.90
     Counter
    0.85
     COUNTER
    0.83
     last
    0.82
    COUNTER
    0.81
    counter
    0.80
     current
    0.79
     terakhir
    0.79
     vorige
    0.78
    Activations Density 0.828%

    No Known Activations