© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4679
    Prev
    Next
    INDEX
    Explanations

    topics related to dietary deficiencies and their associated risks

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

    following "other" or "both"

    np_acts-logits-general · gemini-2.0-flash

    other category labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endwhile
    -0.54
    >//
    -0.51
    pfung
    -0.49
     écologique
    -0.49
    WindowConstants
    -0.48
     avanti
    -0.47
    Aiheesta
    -0.47
    ulemon
    -0.46
     molé
    -0.46
    Encyklopedia
    -0.46
    POSITIVE LOGITS
     miscellaneous
    1.17
     Other
    0.93
     Miscellaneous
    0.93
    Miscellaneous
    0.92
    cellaneous
    0.88
     other
    0.86
    Other
    0.83
     其他
    0.82
    other
    0.82
     category
    0.80
    Activations Density 0.783%

    No Known Activations