© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7904
    Prev
    Next
    INDEX
    Explanations

    terms related to stages of medical conditions or treatments

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

    "Stage" followed by Roman numerals

    np_acts-logits-general · gemini-2.0-flash

    stage followed by roman numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    TagMode
    -0.65
    ecma
    -0.60
     
    -0.54
    égalité
    -0.52
    setFlags
    -0.50
     religieuses
    -0.49
    таратура
    -0.49
    piac
    -0.49
    سياسي
    -0.48
     hur
    -0.48
    POSITIVE LOGITS
     STAGE
    0.91
    coach
    0.85
     Stage
    0.84
    awtextra
    0.79
    Stage
    0.78
     stages
    0.78
    stages
    0.78
    Stages
    0.77
     Stages
    0.77
    STAGE
    0.75
    Activations Density 0.080%

    No Known Activations