© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 39983
    Prev
    Next
    INDEX
    Explanations

    expressions of psychological distress and fear

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

    precautions and avoidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     zufrieden
    -0.43
     aceptación
    -0.34
    Rhestr
    -0.34
    AndEndTag
    -0.32
     acceptance
    -0.31
     success
    -0.31
     surpre
    -0.30
     Keuangan
    -0.30
     satisfa
    -0.30
     satisfaction
    -0.30
    POSITIVE LOGITS
     cautious
    0.86
     Precautions
    0.85
     nightmares
    0.81
     precautions
    0.79
    Precautions
    0.77
     precautionary
    0.77
     avoided
    0.75
     precaution
    0.75
     PTSD
    0.74
     Avoidance
    0.74
    Activations Density 0.106%

    No Known Activations