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. 13194
    Prev
    Next
    INDEX
    Explanations

    references to scientific variables and constants

    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
     Theſe
    -0.95
     ―――――
    -0.91
     Anſ
    -0.84
     Monfieur
    -0.82
    )");
    
    -0.81
     ་་
    -0.81
     ſeveral
    -0.79
     Beſ
    -0.75
     iconFacebook
    -0.74
     iſt
    -0.73
    POSITIVE LOGITS
     V
    2.08
    V
    1.74
     v
    1.61
    getV
    1.45
    v
    0.99
     vanadium
    0.98
     P
    0.97
    IUrlHelper
    0.95
    pV
    0.94
     व
    0.92
    Activations Density 0.139%

    No Known Activations