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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90086
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    ImageContext
    -0.47
     InputDecoration
    -0.41
    ByVersion
    -0.38
     kasarigan
    -0.37
    writeString
    -0.37
     createSprite
    -0.35
    quiao
    -0.35
     carved
    -0.33
     consultato
    -0.32
    sendFile
    -0.32
    POSITIVE LOGITS
    CascadeType
    1.80
    FetchType
    1.63
    TemporalType
    1.23
    centralwidget
    0.99
    RequestOptions
    0.90
    IntoConstraints
    0.89
    MenuInflater
    0.87
    StandardCharsets
    0.85
    sizePolicy
    0.83
    ElementType
    0.82
    Activations Density 0.001%

    No Known Activations