Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11589
    Prev
    Next
    INDEX
    Explanations

    events or gatherings associated with celebrations or ceremonies

    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
     infierno
    -0.46
     commentaire
    -0.44
     geïsole
    -0.43
     Turquía
    -0.42
    จีน
    -0.41
     isolada
    -0.41
     terciopelo
    -0.41
     casero
    -0.41
     présidenti
    -0.39
     tunggal
    -0.39
    POSITIVE LOGITS
     street
    0.72
     sidewalk
    0.65
     plaza
    0.60
     streets
    0.60
     Streets
    0.59
     sidewalks
    0.59
     pedestrian
    0.59
     strolling
    0.58
     NSCoder
    0.56
     downtown
    0.54
    Activations Density 0.205%

    No Known Activations