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. 4-GEMMASCOPE-RES-16K
    6. 710
    Prev
    Next
    INDEX
    Explanations

    legal terminology or concepts related to court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Racine
    -0.93
    ('.'
    -0.90
    ("."
    -0.86
    ی
    -0.79
    LikeLike
    -0.78
                
    -0.77
    Pea
    -0.75
    taget
    -0.74
    Mad
    -0.74
    yah
    -0.74
    POSITIVE LOGITS
     rhestr
    0.84
    complexContent
    0.82
    ècie
    0.82
    PreferredItem
    0.81
     createSprite
    0.80
    lehem
    0.77
    rowave
    0.76
    mored
    0.76
    													
    0.74
     Bethlehem
    0.74
    Activations Density 0.132%

    No Known Activations