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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11275
    Prev
    Next
    INDEX
    Explanations

    references to community involvement and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.42
    ReusableCell
    -0.40
     dày
    -0.36
    ällig
    -0.35
     passend
    -0.34
    CompleteListener
    -0.34
    서는
    -0.34
     Finally
    -0.34
    }")
    
    -0.34
     Découvrez
    -0.33
    POSITIVE LOGITS
     meetup
    0.73
     Meetup
    0.68
     weekly
    0.67
    Meeting
    0.65
    Monthly
    0.64
    Weekly
    0.64
     monthly
    0.62
    weekly
    0.60
    Referral
    0.59
     networking
    0.59
    Activations Density 0.228%

    No Known Activations