© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 13654
    Prev
    Next
    INDEX
    Explanations

    technical terms or metrics related to performance evaluation in a domain such as chemistry or particle physics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    itoneal
    -0.50
     عاما
    -0.47
    dien
    -0.47
     tovább
    -0.45
     brand
    -0.44
     köz
    -0.43
     inf
    -0.42
     already
    -0.42
     jorden
    -0.42
     M
    -0.42
    POSITIVE LOGITS
    Referències
    1.13
     disambiguazione
    0.96
     חיצוניים
    0.91
    tagHelperRunner
    0.88
    PhysRev
    0.88
     NSCoder
    0.83
     <=",
    0.82
    annica
    0.81
    +#+#
    0.81
     autorytatywna
    0.81
    Activations Density 0.061%

    No Known Activations