© 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. 907
    Prev
    Next
    INDEX
    Explanations

    phrases related to resistance against authority and dissent

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

    preceding modal verbs or actions

    np_acts-logits-general · gemini-2.0-flash

    daring to act or speak

    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
    migrationBuilder
    -0.97
    parsedMessage
    -0.80
    følgelig
    -0.78
    UnknownFieldSet
    -0.74
     nahilalakip
    -0.73
    istoitu
    -0.67
    ("]");
    -0.67
    SourceChecksum
    -0.67
    GenerationType
    -0.67
    OGND
    -0.66
    POSITIVE LOGITS
     slightest
    1.22
     touched
    1.14
     touch
    1.05
     dared
    0.91
    touched
    0.90
     touches
    0.90
     touching
    0.88
     moindre
    0.88
    touch
    0.88
     even
    0.86
    Activations Density 0.331%

    No Known Activations