© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3157
    Prev
    Next
    INDEX
    Explanations

    references to health-related services and interventions

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

    following "aerob", "smoke", "cricket", "management"

    np_acts-logits-general · gemini-2.0-flash

    health and medical topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cejas
    -0.35
     définiti
    -0.35
    enderror
    -0.35
     deose
    -0.32
     beat
    -0.31
    rie
    -0.31
     Beat
    -0.31
     casais
    -0.31
     casar
    -0.30
    errorCode
    -0.30
    POSITIVE LOGITS
     transfieras
    0.59
    Autoritní
    0.57
     محفوظة
    0.54
    ipelago
    0.54
    jsonwebtoken
    0.54
    hyrchwyd
    0.53
    ագրություններ
    0.53
     springfox
    0.52
    хьтан
    0.50
    ̈́
    0.50
    Activations Density 0.601%

    No Known Activations