Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 65813
    Prev
    Next
    INDEX
    Explanations

    specific legal terminology or references to court cases

    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
     Akismet
    -0.49
     inſ
    -0.37
     houſe
    -0.36
     viſ
    -0.35
    lossians
    -0.35
    NonQuery
    -0.34
     sche
    -0.34
     colli
    -0.34
     faſt
    -0.34
     ſind
    -0.33
    POSITIVE LOGITS
    ImageContext
    0.66
    ngdoc
    0.61
    LookAnd
    0.60
    Gambas
    0.58
    цездатний
    0.57
    ValueStyle
    0.55
     pinulongan
    0.54
     Wikimedijinoj
    0.51
    sizeCache
    0.51
    IndentedString
    0.50
    Activations Density 0.000%

    No Known Activations