© 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 EvalsExportsinterp-engineNEWAPI 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. 9227
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and speaking actions in the text

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

    Follows a title or honorific

    np_acts-logits-general · gemini-2.0-flash

    polite address

    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
     alcanzado
    -0.46
     grabación
    -0.45
    antle
    -0.44
     useAppContext
    -0.44
     ordination
    -0.44
     prêtres
    -0.43
    슷
    -0.42
     referenties
    -0.41
     Lazy
    -0.41
    朕
    -0.41
    POSITIVE LOGITS
    Respectfully
    0.55
     respectfully
    0.52
     ạ
    0.48
     sir
    0.47
     Respectfully
    0.47
    Sir
    0.45
     Sir
    0.42
     humbly
    0.41
    исленность
    0.38
    sir
    0.38
    Activations Density 0.308%

    No Known Activations