© 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. 28-GEMMASCOPE-RES-16K
    11. 11540
    Prev
    Next
    INDEX
    Explanations

    elements related to personal experiences and introspective moments

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

    Follows determiners like "those" or "that"

    np_acts-logits-general · gemini-2.0-flash

    one of those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.37
    sproz
    -0.36
    //
    -0.36
     hoved
    -0.35
    INSTALLED
    -0.34
    фикация
    -0.34
    serviceWorker
    -0.33
     vents
    -0.32
     embeddings
    -0.32
    Примечания
    -0.32
    POSITIVE LOGITS
    那種
    0.92
     aquela
    0.88
    那种
    0.87
     aquele
    0.85
    的那种
    0.75
    あの
    0.69
    quele
    0.69
    ⓧ
    0.68
     aqueles
    0.68
     pesky
    0.67
    Activations Density 0.326%

    No Known Activations