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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 51857
    Prev
    Next
    INDEX
    Explanations

    phrases related to quality and standards

    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
    MathML
    -0.48
    <?,
    -0.46
     spray
    -0.44
    setOnAction
    -0.44
    eader
    -0.44
    <0xDA>
    -0.43
    istory
    -0.43
    abank
    -0.42
     tweaks
    -0.42
    iastes
    -0.42
    POSITIVE LOGITS
     qualidade
    0.78
     standards
    0.75
     quality
    0.70
    Calidad
    0.69
     qualité
    0.69
    Quality
    0.68
    quality
    0.68
     calidad
    0.68
     Niveau
    0.66
     Quality
    0.65
    Activations Density 0.021%

    No Known Activations