© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1246
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions and related diagnostic terms

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

    existence of issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     angeb
    -0.45
    Quand
    -0.44
    mung
    -0.43
    loem
    -0.42
     mung
    -0.42
     bulundu
    -0.41
    virons
    -0.40
     fully
    -0.40
     indefinitely
    -0.38
    gama
    -0.38
    POSITIVE LOGITS
     any
    0.62
     quelconque
    0.60
     eventuali
    0.49
     الرياضيه
    0.48
    utilisons
    0.47
    有沒有
    0.47
     anything
    0.47
    有任何
    0.47
    IntOverflow
    0.46
     signs
    0.45
    Activations Density 0.074%

    No Known Activations