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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 79008
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and attributes related to webpage formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
     IndexPath
    -0.99
     Дата
    -0.78
    netinet
    -0.54
    ITECH
    -0.36
     derra
    -0.34
     TMPro
    -0.32
     afternoon
    -0.30
     décennies
    -0.30
     copias
    -0.29
    Viited
    -0.29
    POSITIVE LOGITS
     lenker
    3.75
    حياته
    1.52
     cellspacing
    1.37
    حياتها
    1.27
    otus
    1.18
    enumii
    0.80
    fjspx
    0.71
    AndEndTag
    0.71
    KURZBESCHREIBUNG
    0.68
    NSIndexPath
    0.63
    Activations Density 0.000%

    No Known Activations