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. 11-GEMMASCOPE-RES-16K
    6. 7262
    Prev
    Next
    INDEX
    Explanations

    function calls related to retrieving or accessing data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tia
    -1.05
     disambiguazione
    -0.99
    CONSIN
    -0.98
     CardView
    -0.91
     gynhyrchwyd
    -0.85
    ohistochemistry
    -0.84
     Trento
    -0.83
    Farbe
    -0.82
    Tia
    -0.81
     Woodbury
    -0.80
    POSITIVE LOGITS
    ZZZZ
    0.75
     gim
    0.73
     Reinh
    0.68
     klink
    0.67
    empêcher
    0.64
    giphy
    0.64
     Satt
    0.64
     Oude
    0.62
    もしれません
    0.62
     testGet
    0.62
    Activations Density 0.137%

    No Known Activations