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. 5262
    Prev
    Next
    INDEX
    Explanations

    specific terms related to genetics and hybridization in various contexts

    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
     législation
    -0.41
     poderos
    -0.34
     hablado
    -0.33
    历
    -0.32
    期刊论文
    -0.30
     matang
    -0.29
     poderosos
    -0.29
    曆
    -0.29
     vez
    -0.29
     تضيفلها
    -0.29
    POSITIVE LOGITS
    SharedCtor
    0.74
    aarrggbb
    0.65
    enderror
    0.64
     AssemblyCulture
    0.61
    Diweddarwch
    0.59
    oredCriteria
    0.59
    OGND
    0.59
    errHandler
    0.58
    Hentet
    0.56
     ModelExpression
    0.55
    Activations Density 1.697%

    No Known Activations