© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 16065
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific experimentation and molecular biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.69
    TagMode
    -0.62
     تانيه
    -0.61
     Мексичка
    -0.59
     kaarangay
    -0.59
     vectorielles
    -0.58
    Enllaces
    -0.58
    GOTREF
    -0.57
     échange
    -0.57
    jsonwebtoken
    -0.55
    POSITIVE LOGITS
    ViewImports
    0.56
    cino
    0.44
     indisponible
    0.43
    quehanna
    0.43
    uster
    0.42
     BIBSYS
    0.42
    vesh
    0.42
    Made
    0.41
    udnio
    0.41
     käyttö
    0.40
    Activations Density 1.445%

    No Known Activations