© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10399
    Prev
    Next
    INDEX
    Explanations

    concepts related to statistical assumptions and mathematical models

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Beginning of sections introducing methods or results

    np_acts-logits-general · gemini-2.0-flash

    present studies and experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ̍t
    -0.72
     resourceCulture
    -0.64
    nloa
    -0.63
    اریخ
    -0.60
    mybatisplus
    -0.60
    UKAN
    -0.60
     gejala
    -0.60
     lastname
    -0.59
    tonsoft
    -0.58
    čenje
    -0.56
    POSITIVE LOGITS
     discusses
    0.62
     discuss
    0.58
     tests
    0.57
     demonstrate
    0.55
     illustrate
    0.55
     demonstrates
    0.55
    demon
    0.54
     illustrations
    0.54
     illustrates
    0.53
    __":
    0.51
    Activations Density 0.780%

    No Known Activations