© 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. 11438
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology and cellular mechanisms

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

    Preceding "new," "novel," or "unique"

    np_acts-logits-general · gemini-2.0-flash

    provide new insights

    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
    案
    -0.60
    According
    -0.49
    PLANATION
    -0.47
     fórmula
    -0.46
     According
    -0.45
     giud
    -0.45
     stats
    -0.45
     checked
    -0.45
     according
    -0.43
    chot
    -0.43
    POSITIVE LOGITS
     paradigms
    0.77
     molecular
    0.73
     CreateTagHelper
    0.72
    vances
    0.70
     fundamental
    0.68
     exploiting
    0.68
    fundamental
    0.68
     advances
    0.68
     paradigma
    0.68
     mechanistic
    0.67
    Activations Density 2.571%

    No Known Activations