© 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. 39-GEMMASCOPE-RES-16K
    11. 1483
    Prev
    Next
    INDEX
    Explanations

    details related to violent death and its circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     injured
    -0.63
     blessés
    -0.57
     injuring
    -0.55
    受伤
    -0.55
    injured
    -0.54
     wounded
    -0.54
     verletzt
    -0.53
     injure
    -0.52
     blessé
    -0.52
     hurting
    -0.52
    POSITIVE LOGITS
     suicide
    0.68
     strang
    0.63
     suff
    0.62
     drowning
    0.60
     complications
    0.58
     choking
    0.55
    suicide
    0.54
     suicides
    0.54
     Suicide
    0.54
    Suicide
    0.53
    Activations Density 0.665%

    No Known Activations