© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58236
    Prev
    Next
    INDEX
    Explanations

    references to segments or segmentation in a specific context, suggesting a focus on structured data or analysis techniques

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

    segment, segmental

    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
    <bos>
    -0.49
     públicas
    -0.44
     darah
    -0.44
     FileNotFound
    -0.42
     dört
    -0.40
     nước
    -0.40
     Flüs
    -0.39
    dry
    -0.39
     Públicas
    -0.38
     recours
    -0.38
    POSITIVE LOGITS
     Segment
    1.36
    Segment
    1.27
     segment
    1.26
    segment
    1.23
     Segments
    1.21
     segments
    1.10
    segments
    0.97
    Segments
    0.94
    SEGMENT
    0.93
     segmento
    0.93
    Activations Density 0.006%

    No Known Activations