© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5282
    Prev
    Next
    INDEX
    Explanations

    references to suicide or self-harm

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

    descriptions of hanging, suspension, or situations involving ropes around necks.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     nh
    -0.32
     intérêt
    -0.31
    domésticos
    -0.30
     hadir
    -0.28
    intérêt
    -0.28
     meres
    -0.28
     davanti
    -0.27
    盛り
    -0.27
     aans
    -0.26
     آش
    -0.25
    POSITIVE LOGITS
     climbing
    1.55
     climb
    1.42
     climbed
    1.37
     Climbing
    1.34
     climbs
    1.28
    climbing
    1.28
    Climbing
    1.28
    climb
    1.27
     climber
    1.20
     Climb
    1.18
    Activations Density 0.260%

    No Known Activations