Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13369
    Prev
    Next
    INDEX
    Explanations

    names and identifiers related to characters and aliases

    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
    AddHtmlAttribute
    -0.61
    ")){
    
    -0.54
    )](
    -0.51
     pylori
    -0.49
    存于互联网档案馆
    -0.49
     implementation
    -0.49
    ApiModel
    -0.49
    )";
    
    -0.48
     proxim
    -0.48
    )");
    
    -0.47
    POSITIVE LOGITS
    randrange
    0.69
     disguise
    0.66
    rungsseite
    0.64
    disfraz
    0.61
    tvguidetime
    0.60
     BioLib
    0.59
     disgu
    0.57
    withIdentifier
    0.57
     metamorphosis
    0.56
     Вікіпе
    0.56
    Activations Density 0.408%

    No Known Activations