© 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. 1031
    Prev
    Next
    INDEX
    Explanations

    expressions related to fear of consequences or repercussions in various contexts

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

    risks or negative outcomes

    np_acts-logits-general · gemini-2.0-flash

    risk and harm

    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
    <bos>
    -0.63
     autorytatywna
    -0.56
    HideFlags
    -0.55
     StatefulWidget
    -0.54
    HasBeenSet
    -0.54
    Климат
    -0.53
    fiées
    -0.53
    FunctionFlags
    -0.52
     TestBed
    -0.52
     gubern
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.95
     risk
    0.85
     risking
    0.83
     harm
    0.83
     jeopardi
    0.80
     jeopardize
    0.78
     risked
    0.78
    万一
    0.76
     potentially
    0.76
     lose
    0.73
    Activations Density 0.481%

    No Known Activations