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. 6495
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical appearance and emotional expressions

    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
    StreetMap
    -0.54
    ViewImports
    -0.54
    CreateModel
    -0.52
    ствий
    -0.51
    WithFormat
    -0.50
    fgets
    -0.50
    sizeCache
    -0.49
     Linder
    -0.49
    reonine
    -0.48
    Kjelder
    -0.48
    POSITIVE LOGITS
     eyes
    1.88
     Eyes
    1.51
    eyes
    1.45
     EYES
    1.44
    Eyes
    1.41
     eye
    1.36
     Eye
    1.23
    Eye
    1.19
     ojos
    1.19
     eyed
    1.19
    Activations Density 0.118%

    No Known Activations