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. 5-GEMMASCOPE-RES-16K
    6. 11769
    Prev
    Next
    INDEX
    Explanations

    complex sentence structures or specific grammar patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pingback
    -0.54
    。
    -0.53
    
    -0.53
    ειτουργ
    -0.50
    PerformLayout
    -0.48
    kriegs
    -0.47
    ".
    -0.47
    '.
    -0.47
     daher
    -0.46
    EDES
    -0.46
    POSITIVE LOGITS
     otomatig
    0.70
    DebuggerNonUser
    0.64
    protoimpl
    0.62
     '\\;'
    0.62
     nahilalakip
    0.59
    Vidite
    0.58
    GraphicsUnit
    0.58
     estekak
    0.58
    __(/*!
    0.57
     BoxFit
    0.55
    Activations Density 1.161%

    No Known Activations