© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 236
    Prev
    Next
    INDEX
    Explanations

    references to cells and cellular structures

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

    "Cell" followed by related scientific or technological terms

    np_acts-logits-general · gemini-2.0-flash

    cell phone or cell biology contexts

    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
    antMatchers
    -0.79
     Wikimedijinoj
    -0.79
    CreateMap
    -0.79
     Administrativna
    -0.75
    ⪢
    -0.74
     ivelany
    -0.72
    onomía
    -0.71
    RetentionPolicy
    -0.71
    fulness
    -0.71
     Réponses
    -0.70
    POSITIVE LOGITS
    Cells
    0.85
     cells
    0.85
    cells
    0.83
     Cells
    0.83
    phones
    0.81
    CELL
    0.80
     phone
    0.77
     phones
    0.75
    phone
    0.74
    ulo
    0.73
    Activations Density 0.185%

    No Known Activations