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. 5780
    Prev
    Next
    INDEX
    Explanations

    specific conditions or preferences associated with products or populations

    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
     سكانية
    -0.69
    Lähteet
    -0.63
    DebuggerStep
    -0.62
    OfWork
    -0.54
     незавершена
    -0.54
    ErrUnexpectedEOF
    -0.52
    Примітки
    -0.51
     aceton
    -0.50
     protoimpl
    -0.49
    czas
    -0.49
    POSITIVE LOGITS
     Particularly
    0.66
     particularly
    0.64
     Особенно
    0.62
    particularly
    0.58
    >");
    
    0.54
     especially
    0.54
    ticularly
    0.53
     mocno
    0.52
     Especially
    0.51
    RenderAtEndOf
    0.51
    Activations Density 0.368%

    No Known Activations