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. 4-GEMMASCOPE-RES-16K
    6. 10506
    Prev
    Next
    INDEX
    Explanations

    references to various foundations and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -1.03
     Bengals
    -0.92
    luigi
    -0.90
     Scrolls
    -0.87
     Мексичка
    -0.86
     Whigs
    -0.85
     végétale
    -0.84
    extAlignment
    -0.84
    goog
    -0.84
     Whig
    -0.84
    POSITIVE LOGITS
     foundation
    2.84
     Foundation
    2.81
    Foundation
    2.64
    foundation
    2.58
     foundations
    2.52
     FOUNDATION
    2.51
     Foundations
    2.31
    Foundations
    2.21
     fondation
    1.64
     foundational
    1.60
    Activations Density 0.056%

    No Known Activations