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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 13629
    Prev
    Next
    INDEX
    Explanations

    structures and components of code, specifically related to programming and algorithmic logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     less
    -1.12
     Less
    -1.08
     Below
    -1.07
     below
    -1.07
    Less
    -1.06
    below
    -1.06
     mindre
    -1.06
    Below
    -1.05
    less
    -0.97
     fewer
    -0.95
    POSITIVE LOGITS
     >=
    0.98
     ≥
    0.84
     greater
    0.81
     >
    0.79
    ≥
    0.78
    >=
    0.77
     above
    0.70
     $>
    0.70
    ]>=
    0.68
    geq
    0.66
    Activations Density 0.861%

    No Known Activations