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. 11-GEMMASCOPE-RES-16K
    6. 5743
    Prev
    Next
    INDEX
    Explanations

    terms related to physics and scientific qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.81
    <tr>
    -0.77
     STC
    -0.77
    ostok
    -0.67
    writerow
    -0.66
    kháu
    -0.65
    SRS
    -0.65
    存于互联网档案馆
    -0.63
     Dada
    -0.63
     Dund
    -0.63
    POSITIVE LOGITS
     Ph
    1.44
    Ph
    1.42
     Phillies
    1.30
     PH
    1.28
     ph
    1.27
    PH
    1.26
     Philo
    1.24
     Φ
    1.20
     PHO
    1.17
     Phillips
    1.17
    Activations Density 0.350%

    No Known Activations