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. 14-GEMMASCOPE-RES-16K
    6. 13006
    Prev
    Next
    INDEX
    Explanations

    statements about problems or situations where there is a concern or issue being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.76
     ſtate
    -0.67
    ingly
    -0.66
     intptr
    -0.65
    omeness
    -0.64
     Delphi
    -0.63
    fjspx
    -0.63
     ſever
    -0.63
     kina
    -0.62
     ddelweddau
    -0.61
    POSITIVE LOGITS
     that
    0.78
    :
    0.62
    invokeLater
    0.59
     disambiguazione
    0.55
    principalColumn
    0.54
     contactez
    0.49
     cioccolato
    0.48
    PageFactory
    0.47
     ویکی‌پدیا
    0.47
     desenhos
    0.46
    Activations Density 0.145%

    No Known Activations