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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13003
    Prev
    Next
    INDEX
    Explanations

    descriptions of materials and their compositions

    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
     garantías
    -0.34
    SequentialGroup
    -0.33
     Dampf
    -0.32
    ละ
    -0.31
    日閲覧
    -0.31
     Krieg
    -0.29
     théorie
    -0.29
    イヤー
    -0.28
    glBind
    -0.28
    Binding
    -0.27
    POSITIVE LOGITS
    Personendaten
    0.73
     AssemblyCulture
    0.69
    RegressionTest
    0.68
    ніципалі
    0.66
    shaped
    0.65
     CGSize
    0.61
     виправивши
    0.61
    Shaped
    0.61
    期刊论文
    0.60
    ształ
    0.60
    Activations Density 0.692%

    No Known Activations