© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 14828
    Prev
    Next
    INDEX
    Explanations

    negation and dismissive attitudes toward certain racial discussions

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

    negation and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     autorytatywna
    -0.59
    quelize
    -0.58
    oa̍t
    -0.54
     Wicidata
    -0.53
    rrggbb
    -0.51
    tagHelperRunner
    -0.50
     فريبيس
    -0.49
    ftagPool
    -0.47
    تقاوى
    -0.46
    XmlAccessorType
    -0.46
    POSITIVE LOGITS
     toxic
    0.41
    SBATCH
    0.40
    AutoField
    0.37
    screen
    0.36
     Auto
    0.35
     angry
    0.35
    fbc
    0.35
    DropColumn
    0.35
     blot
    0.35
    Axis
    0.35
    Activations Density 0.076%

    No Known Activations