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

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 9749
    Prev
    Next
    INDEX
    Explanations

    conditions related to thread management and boolean logic in code

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

    Code keywords: break, continue, return

    np_acts-logits-general · gemini-2.0-flash

    unit areas, cannot say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    品です
    -0.33
     home
    -0.33
     quaisquer
    -0.33
     tuyo
    -0.32
     veilig
    -0.32
     fiebre
    -0.32
     Atas
    -0.31
     thuis
    -0.31
     irmãos
    -0.31
     dintre
    -0.31
    POSITIVE LOGITS
    break
    1.09
     break
    1.01
    continue
    0.84
     Break
    0.79
    BREAK
    0.75
     BREAK
    0.74
    Break
    0.72
     breaks
    0.71
     breaking
    0.70
     Breaks
    0.69
    Activations Density 0.106%

    No Known Activations