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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5193
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and financial matters

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     usually
    -0.33
     typically
    -0.33
    पया
    -0.32
     సౌకర్య
    -0.31
    ఔ
    -0.30
    iestety
    -0.30
    われました
    -0.29
     gjerne
    -0.29
     Typically
    -0.29
     perhaps
    -0.29
    POSITIVE LOGITS
     nahilalakip
    0.72
    OGND
    0.66
    tagHelperRunner
    0.66
     kasarigan
    0.63
    intios
    0.63
    ACHUSET
    0.62
    AddTagHelper
    0.60
    期刊论文
    0.59
    parsedMessage
    0.58
    MessageTagHelper
    0.58
    Activations Density 0.746%

    No Known Activations