© 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. 1-GEMMASCOPE-RES-16K
    11. 8154
    Prev
    Next
    INDEX
    Explanations

    terms related to damage or harmful effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.56
    colgante
    -0.50
     sintético
    -0.47
     yayın
    -0.43
    retudo
    -0.42
    videz
    -0.42
     поя
    -0.41
     vendidos
    -0.41
    pannt
    -0.41
    velser
    -0.40
    POSITIVE LOGITS
     damaging
    1.13
     destructive
    1.07
     Dama
    1.00
    destructive
    0.96
     harmful
    0.94
    Dama
    0.94
    dama
    0.93
     Harmful
    0.81
    Harmful
    0.78
     Damage
    0.77
    Activations Density 0.372%

    No Known Activations