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. 12949
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in sentences

    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
    __":
    
    -0.85
     étoient
    -0.69
    uxxxx
    -0.68
    ChildScrollView
    -0.68
    __':
    
    -0.67
    $_['
    -0.63
    EDEFAULT
    -0.63
     Theſe
    -0.62
    EndProject
    -0.62
    AutoresizingMask
    -0.62
    POSITIVE LOGITS
     away
    0.63
     forward
    0.62
     up
    0.62
     onward
    0.60
    up
    0.59
    era
    0.54
     ahead
    0.52
     back
    0.51
    ass
    0.50
     things
    0.49
    Activations Density 0.034%

    No Known Activations