© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 81567
    Prev
    Next
    INDEX
    Explanations

    the output stream operator in code, indicating it is focused on situations involving printing to the standard output

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

    C++ std::endl median

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     RPS
    -0.66
    providedIn
    -0.63
     ARB
    -0.63
     ALP
    -0.60
     المعيارى
    -0.59
    RPS
    -0.59
    BPM
    -0.59
     FES
    -0.59
     APM
    -0.59
    %)$
    -0.56
    POSITIVE LOGITS
     <<
    1.14
    ()<<
    0.88
    <<
    0.86
    )<<
    0.72
    <<<<
    0.70
    ]<<
    0.69
    "<<
    0.60
     "<<
    0.59
     étan
    0.59
     <<=
    0.58
    Activations Density 0.007%

    No Known Activations