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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3468
    Prev
    Next
    INDEX
    Explanations

    the beginning of segments in text

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

    Code snippets and names

    np_acts-logits-general · gemini-2.0-flash

    data transmission

    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
    Referências
    -0.66
     far
    -0.58
     bien
    -0.58
    Catatan
    -0.55
     sur
    -0.54
     trang
    -0.53
     Therefore
    -0.53
     est
    -0.52
     secara
    -0.52
    Referencoj
    -0.51
    POSITIVE LOGITS
     Shakspeare
    1.12
    enderror
    1.01
     Cæsar
    0.97
    ftagPool
    0.96
     Shaksp
    0.89
     myſelf
    0.85
     للاسماء
    0.83
     Moslem
    0.81
     Euphrates
    0.81
     Ophelia
    0.81
    Activations Density 0.137%

    No Known Activations