© 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. 24-GEMMASCOPE-RES-16K
    11. 6590
    Prev
    Next
    INDEX
    Explanations

    mentions of various roles and relationships within organizations or teams

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

    preceding "temporarily", "through", "in", "at", etc

    np_acts-logits-general · gemini-2.0-flash

    legal and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     register
    -0.42
    register
    -0.40
     Register
    -0.38
     Lem
    -0.38
    不一样的
    -0.36
    ク
    -0.36
     gosto
    -0.35
    ようになる
    -0.35
     brighter
    -0.35
     exemplary
    -0.34
    POSITIVE LOGITS
    complexContent
    0.66
     altogether
    0.60
     AssemblyTitle
    0.59
     تانيه
    0.57
    UnusedPrivate
    0.56
     ब्रेकडाउन
    0.56
     ExecuteAsync
    0.56
    WriteBarrier
    0.55
    parsedMessage
    0.53
     kasarigan
    0.52
    Activations Density 0.802%

    No Known Activations