© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3101
    Prev
    Next
    INDEX
    Explanations

    references to consulting healthcare professionals or seeking medical advice

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    instructions about medical consultations and following medical advice.

    oai_token-act-pair · claude-3-5-haiku-20241022
    Triggered by @neilrathi

    instructions to contact a doctor or healthcare provider for medical advice.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     createSlice
    -0.49
    founders
    -0.46
    preneurs
    -0.43
     founders
    -0.42
    fighters
    -0.42
     ligiloj
    -0.40
    Executives
    -0.40
     runners
    -0.40
     golfers
    -0.40
    matchCondition
    -0.39
    POSITIVE LOGITS
     nearest
    0.62
     trusted
    0.60
     local
    0.58
    +#+
    0.58
    nearest
    0.54
     authorized
    0.53
     appropriate
    0.53
     qualified
    0.52
     licensed
    0.52
     authorised
    0.51
    Activations Density 0.339%

    No Known Activations