© 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. 22-GEMMASCOPE-RES-16K
    6. 14155
    Prev
    Next
    INDEX
    Explanations

    references to medical stages in disease progression

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

    "Stage" and roman numerals

    np_acts-logits-general · gemini-2.0-flash

    stage with numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sproble
    -0.59
     
    -0.58
    innen
    -0.55
    orsese
    -0.55
    پیوند
    -0.54
    luan
    -0.54
    piac
    -0.53
     Janeiro
    -0.53
    )));
    
    -0.52
    ató
    -0.52
    POSITIVE LOGITS
    coach
    1.06
     STAGE
    1.02
     stages
    0.98
     Stage
    0.97
    Stages
    0.95
     Stages
    0.95
    stages
    0.91
    Stage
    0.88
    stage
    0.84
     stage
    0.84
    Activations Density 0.037%

    No Known Activations