© 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 - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3581
    Prev
    Next
    INDEX
    Explanations

    phrases and terms indicating levels or conditions relating to worth, achievement, or social statuses

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

    Comes after the word "of"

    np_acts-logits-general · gemini-2.0-flash

    formal scientific terms

    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
     the
    -0.51
     Kecil
    -0.35
     cubierto
    -0.35
     jefes
    -0.33
     seura
    -0.33
     Jerusalén
    -0.32
     viime
    -0.32
     Gegenwart
    -0.31
     puesta
    -0.31
     Desenvolvimento
    -0.31
    POSITIVE LOGITS
    parsedMessage
    0.89
    WireFormatLite
    0.86
     queſta
    0.85
     للمعارف
    0.85
    migrationBuilder
    0.78
    featureID
    0.77
    Билгалдахарш
    0.76
    ſicht
    0.76
    ftagPool
    0.75
    UIControlState
    0.73
    Activations Density 0.663%

    No Known Activations