© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14787
    Prev
    Next
    INDEX
    Explanations

    actions related to physical vulnerability and restraint

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

    Body positions (lying, kneeling, reclined)

    np_acts-logits-general · gemini-2.0-flash

    body positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.46
    withIdentifier
    -0.39
    Хьажоргаш
    -0.35
    AddTagHelper
    -0.33
    škai
    -0.32
    Kariera
    -0.32
    cenzo
    -0.29
    termilk
    -0.29
    verifyException
    -0.28
     كومونز
    -0.28
    POSITIVE LOGITS
     lying
    1.07
     Lying
    0.93
     prostrate
    0.91
     kneeling
    0.86
     laying
    0.82
    Lying
    0.81
     lie
    0.81
     prone
    0.79
    lying
    0.77
     kneel
    0.77
    Activations Density 0.235%

    No Known Activations