© 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. 23-GEMMASCOPE-RES-16K
    11. 2576
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to functions and their return values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.92
     للمعارف
    -0.91
     يتيمه
    -0.86
    AndEndTag
    -0.84
    parsedMessage
    -0.83
    Tikang
    -0.78
    <unused8>
    -0.77
    <unused41>
    -0.77
    [@BOS@]
    -0.77
    <pad>
    -0.77
    POSITIVE LOGITS
      
    0.38
     //
    0.35
     (
    0.32
    //
    0.32
    underbrace
    0.32
    （
    0.32
    =
    0.31
    <strong>
    0.29
    ();//
    0.29
    Remember
    0.28
    Activations Density 0.266%

    No Known Activations