© 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. 12-GEMMASCOPE-RES-16K
    11. 13367
    Prev
    Next
    INDEX
    Explanations

    phrases and terms that convey skepticism or criticism towards mainstream narratives, especially those related to marginalized groups and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -1.04
    kuuta
    -0.66
    ChildIndex
    -0.64
    BagLayout
    -0.63
    getColumnIndex
    -0.54
    SQLiteDatabase
    -0.50
     remonter
    -0.50
    kiat
    -0.49
     ModelExpression
    -0.49
    דו
    -0.48
    POSITIVE LOGITS
     hypocrite
    0.67
     moron
    0.62
     coward
    0.61
     idiotic
    0.60
     cowardly
    0.60
     cowards
    0.59
     crap
    0.59
     idiot
    0.59
     ProtoMessage
    0.58
     morons
    0.58
    Activations Density 0.710%

    No Known Activations