© 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. 31-GEMMASCOPE-RES-131K
    11. 70391
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "forbidden" or taboo subjects

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

    things that are forbidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.53
    ViewInit
    -0.52
     patrulla
    -0.45
     liderazgo
    -0.45
     ainfi
    -0.44
    sianic
    -0.43
    ypus
    -0.43
    Leaders
    -0.42
    restes
    -0.42
    Team
    -0.42
    POSITIVE LOGITS
     Forbidden
    0.75
     forbidden
    0.74
    Forbidden
    0.65
     forbid
    0.62
     forbids
    0.60
     forbade
    0.60
     prohibited
    0.59
    forbidden
    0.57
     toegang
    0.54
     forbidding
    0.52
    Activations Density 0.008%

    No Known Activations