© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105348
    Prev
    Next
    INDEX
    Explanations

    elements related to data validation criteria in programming

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
     سكانية
    -0.48
    Aiheesta
    -0.41
     برانيه
    -0.40
     препратки
    -0.40
    olol
    -0.40
    standing
    -0.40
    tellers
    -0.38
     дописавши
    -0.38
    LikeLike
    -0.38
     esternos
    -0.38
    POSITIVE LOGITS
     autorytatywna
    0.64
    ⤹
    0.52
    ftagPool
    0.47
    addPreferredGap
    0.45
    fjspx
    0.44
    WriteTagHelper
    0.44
    StructEnd
    0.43
    밌
    0.43
    nadequate
    0.43
     unstable
    0.42
    Activations Density 0.002%

    No Known Activations