© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1531
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to clinical trials and mental health conditions

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

    before periods

    np_acts-logits-general · gemini-2.0-flash

    medical trial or surgery concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pad
    -0.36
     coordinate
    -0.35
    faced
    -0.34
    ++]
    -0.34
     vle
    -0.34
    FUL
    -0.33
    )=>{
    -0.33
     grat
    -0.33
     sta
    -0.33
     ngh
    -0.33
    POSITIVE LOGITS
    rungsseite
    0.62
     विश्वसनीयता
    0.54
     avoient
    0.53
     feroit
    0.53
     Monfieur
    0.52
     Verſ
    0.52
    يكب
    0.52
     Beſ
    0.50
    KommentareTeilen
    0.50
     Geſch
    0.50
    Activations Density 1.167%

    No Known Activations