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. 117341
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of considering multiple factors or variables

    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
     proprement
    -0.63
    medriver
    -0.57
    AnimationsModule
    -0.57
    ientras
    -0.56
     mijne
    -0.55
    MigrationBuilder
    -0.54
     resourceCulture
    -0.54
    parsedMessage
    -0.54
     Administrativna
    -0.54
     مشين
    -0.53
    POSITIVE LOGITS
     considerations
    0.71
     consideration
    0.66
     consider
    0.65
    consider
    0.64
     considering
    0.63
     учитывать
    0.59
    CONSIDER
    0.59
    Consider
    0.59
     Considerations
    0.59
     учетом
    0.59
    Activations Density 0.030%

    No Known Activations