© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42707
    Prev
    Next
    INDEX
    Explanations

    elements related to lists or structured data

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

    related to both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    WireFormatLite
    -0.60
    tinyos
    -0.50
    OGND
    -0.50
    Holo
    -0.41
    TargetException
    -0.39
    penta
    -0.37
    InternalFrame
    -0.37
     Roskov
    -0.36
     Arxivat
    -0.36
    UnusedPrivate
    -0.36
    POSITIVE LOGITS
     ambos
    0.55
     båda
    0.53
    تقاوى
    0.46
    Ambos
    0.46
    どちら
    0.44
    脚注の使い方
    0.44
     beiden
    0.44
     both
    0.43
     begge
    0.43
     entrambi
    0.43
    Activations Density 0.027%

    No Known Activations