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. 1539
    Prev
    Next
    INDEX
    Explanations

    concepts related to unity and collaboration, particularly in a religious or communal context

    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
     await
    -0.39
    AndEndTag
    -0.36
    bewerken
    -0.35
     escape
    -0.31
    tinyos
    -0.31
    něž
    -0.30
     especializado
    -0.29
    文獻
    -0.29
     lü
    -0.28
     circuit
    -0.28
    POSITIVE LOGITS
     uniting
    0.90
     unified
    0.79
     unifying
    0.79
     united
    0.77
     unification
    0.74
     unity
    0.73
    Unified
    0.72
     unify
    0.69
     unites
    0.68
     unite
    0.67
    Activations Density 0.305%

    No Known Activations