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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5842
    Prev
    Next
    INDEX
    Explanations

    references to competitive sports events, specifically cups and championships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cshtml
    -0.59
    ropoda
    -0.55
     sos
    -0.54
     MPR
    -0.53
     unt
    -0.53
    WithIdentifier
    -0.52
     monoch
    -0.52
     Brandenburg
    -0.51
     Tampoco
    -0.51
     Assist
    -0.51
    POSITIVE LOGITS
     Cup
    3.09
    Cup
    2.59
     cup
    2.58
     CUP
    2.39
    cup
    2.22
     Cups
    2.21
     cups
    1.93
    CUP
    1.79
    カップ
    1.68
    cups
    1.54
    Activations Density 0.055%

    No Known Activations