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. 3073
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific methodologies and details about experiments

    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
    SharedCtor
    -0.55
    SizeF
    -0.52
    ActiveRecord
    -0.52
    MessageState
    -0.51
    idać
    -0.49
    들은
    -0.48
    yamaha
    -0.48
     réglable
    -0.48
    WEB
    -0.48
    layoutControl
    -0.47
    POSITIVE LOGITS
     '\\;'
    0.75
     ویکی‌پدیای
    0.72
    хьтан
    0.71
     שוליים
    0.71
     дописавши
    0.70
    principalColumn
    0.68
     astore
    0.65
     Вікіпе
    0.64
     ujednoznacz
    0.63
    enumii
    0.63
    Activations Density 1.227%

    No Known Activations