© 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 EvalsExportsinterp-engineNEWAPI 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. 18658
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or derogatory language towards people

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

    insults and derogatory terms

    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
    хьтан
    -0.66
     referenties
    -0.64
     protoimpl
    -0.63
    complexContent
    -0.62
    setContentView
    -0.59
    parsedMessage
    -0.58
     يتيمه
    -0.58
     ujednoznacz
    -0.57
    oredCriteria
    -0.57
     Administrativna
    -0.56
    POSITIVE LOGITS
     idiot
    1.54
     idiots
    1.44
     fools
    1.30
     Idiot
    1.25
     fool
    1.23
    Idiot
    1.20
    idiot
    1.19
     morons
    1.17
     moron
    1.17
     stupid
    1.16
    Activations Density 0.079%

    No Known Activations