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. 33-GEMMASCOPE-RES-131K
    6. 65895
    Prev
    Next
    INDEX
    Explanations

    elements related to user communication and information sharing

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     negative
    -0.45
     Negative
    -0.43
    setSize
    -0.41
     NEGATIVE
    -0.40
    YSIS
    -0.40
    Negative
    -0.40
     everywhere
    -0.39
    czar
    -0.38
     Crédito
    -0.37
     dough
    -0.36
    POSITIVE LOGITS
    AnimationsModule
    0.68
    AsUp
    0.60
     promotional
    0.59
     promotions
    0.56
     Promotions
    0.54
    LookAnd
    0.54
     announcements
    0.54
    Promotions
    0.54
     Updates
    0.53
     Promotional
    0.53
    Activations Density 0.019%

    No Known Activations