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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12155
    Prev
    Next
    INDEX
    Explanations

    expressions of positive sentiment and well-wishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     تانيه
    -0.67
    ecé
    -0.62
     ngl
    -0.57
    ğraf
    -0.56
    dolu
    -0.55
     comigo
    -0.55
     Зачем
    -0.55
    FieldBuilder
    -0.55
    ็จ
    -0.55
     gddr
    -0.53
    POSITIVE LOGITS
     wünsche
    0.63
     always
    0.58
    endsection
    0.57
     sehat
    0.56
     health
    0.55
    GenerationType
    0.54
    vábbi
    0.53
    VersionUID
    0.53
    numerusform
    0.53
    HEALTH
    0.53
    Activations Density 0.099%

    No Known Activations