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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 6376
    Prev
    Next
    INDEX
    Explanations

    references to negative consequences or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.59
     nahilalakip
    -0.53
     defaultstate
    -0.52
     beaming
    -0.51
    complexContent
    -0.51
    rrggbb
    -0.48
    Satis
    -0.47
     Inspiration
    -0.47
     individuality
    -0.46
     Milestone
    -0.46
    POSITIVE LOGITS
     Gewalt
    0.55
     victims
    0.54
     violent
    0.53
     victime
    0.52
     violence
    0.51
    locaust
    0.50
     violenta
    0.50
     violen
    0.49
     Violent
    0.49
    terror
    0.49
    Activations Density 2.992%

    No Known Activations