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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15465
    Prev
    Next
    INDEX
    Explanations

    references to measurements and descriptions of size in relation to animals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.64
    ContentAsync
    -0.60
    aarrggbb
    -0.57
     تضيفلها
    -0.56
    EnableWeb
    -0.56
    PostMapping
    -0.55
     magasiner
    -0.54
     return
    -0.53
     Alcott
    -0.52
     Bateman
    -0.50
    POSITIVE LOGITS
     büyü
    0.73
    basicConfig
    0.66
     stør
    0.61
     sqlalchemy
    0.61
     weighing
    0.60
     averaging
    0.60
    getMock
    0.59
     péld
    0.59
     Growth
    0.58
     cappello
    0.58
    Activations Density 0.036%

    No Known Activations