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. 626
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to certification and credentials

    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
    cluse
    -0.80
     drey
    -0.75
    PreferredItem
    -0.70
    KommentareTeilen
    -0.70
     Pote
    -0.67
    ophage
    -0.67
    Xna
    -0.67
    sedown
    -0.65
     Opposition
    -0.65
     arrang
    -0.65
    POSITIVE LOGITS
     certification
    2.24
     certified
    2.17
     certificate
    2.10
     certify
    2.08
     certificates
    2.06
    certified
    2.05
     certifications
    2.04
     certific
    1.99
     Certification
    1.97
    certification
    1.96
    Activations Density 0.103%

    No Known Activations