© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 27748
    Prev
    Next
    INDEX
    Explanations

    references to threats or intimidation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    threats, threatening, threatened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    InputBorder
    -0.67
    EndInit
    -0.66
    AnchorStyles
    -0.56
     EconPapers
    -0.55
    ']>;
    -0.54
    DockStyle
    -0.51
    ResumeLayout
    -0.51
    OrNil
    -0.50
    IsMutable
    -0.50
     ſind
    -0.50
    POSITIVE LOGITS
     threats
    1.30
     Threats
    1.02
    Threats
    0.98
     amenazas
    0.79
     threatening
    0.79
     threatened
    0.74
    threat
    0.73
     threaten
    0.72
     insults
    0.68
     threatens
    0.66
    Activations Density 0.006%

    No Known Activations