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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    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. 25073
    Prev
    Next
    INDEX
    Explanations

    technical or programming-related keywords and indicators

    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
     EconPapers
    -0.73
    AutoScale
    -0.68
    DOCTYPE
    -0.59
    __':
    
    -0.58
    mappedBy
    -0.57
     MonoBehaviour
    -0.56
    TestingModule
    -0.55
     endwhile
    -0.55
    Ссылки
    -0.52
    setupUi
    -0.52
    POSITIVE LOGITS
     Temos
    0.58
     pleaſure
    0.57
     Pilate
    0.54
    pters
    0.54
     Majefty
    0.53
     Please
    0.50
     Hokkaido
    0.49
     illus
    0.49
     pending
    0.49
     fevere
    0.49
    Activations Density 0.186%

    No Known Activations