© 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. 24-GEMMASCOPE-RES-16K
    11. 1172
    Prev
    Next
    INDEX
    Explanations

    phrases concerning child-friendly dietary options and related health considerations

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

    simple or lightweight things

    np_acts-logits-general · gemini-2.0-flash

    simple, light, low, thin

    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
     käytet
    -0.47
    Bes
    -0.42
     блока
    -0.38
     ناخ
    -0.38
    jaw
    -0.37
     suddenly
    -0.36
    adpleegd
    -0.36
     plötzlich
    -0.36
    aterin
    -0.36
    writeField
    -0.35
    POSITIVE LOGITS
    VersionUID
    0.57
     modular
    0.50
     lightweight
    0.48
    Билгалдахарш
    0.48
     adaptable
    0.46
     designs
    0.46
     minimalist
    0.46
     robust
    0.46
     simpler
    0.46
     lighter
    0.45
    Activations Density 0.448%

    No Known Activations