© 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. 20-GEMMASCOPE-RES-16K
    11. 16238
    Prev
    Next
    INDEX
    Explanations

    references to health assessments and conditions associated with diabetes

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

    Followed by words like "should" or expressing a need

    np_acts-logits-general · gemini-2.0-flash

    condition mRNApeople shouldusing provethe affectedmight 7

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :+:
    -0.76
     cherchés
    -0.66
    GTCX
    -0.64
    ngrx
    -0.60
     –,
    -0.58
     kautta
    -0.57
     efectivamente
    -0.56
    AutoScaleMode
    -0.55
     الحره
    -0.53
     <=",
    -0.53
    POSITIVE LOGITS
     
    0.63
     Symptoms
    0.60
     fusca
    0.57
     Normal
    0.57
     What
    0.57
     https
    0.54
     How
    0.54
     Blood
    0.53
     Menteri
    0.52
     archbishop
    0.52
    Activations Density 0.036%

    No Known Activations