© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 5631
    Prev
    Next
    INDEX
    Explanations

    references to institutions, particularly universities, and their historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.67
     PIER
    -0.57
    hnia
    -0.56
     alder
    -0.53
    onshire
    -0.53
    Sheffield
    -0.53
     Finnish
    -0.52
     Finns
    -0.50
     Sheffield
    -0.49
     Evanston
    -0.49
    POSITIVE LOGITS
     Telangana
    0.96
     Hyderabad
    0.84
     Andhra
    0.77
    Hyderabad
    0.76
     Telugu
    0.74
     TDP
    0.74
     AP
    0.68
     YS
    0.68
     Gunt
    0.68
    Tel
    0.67
    Activations Density 0.106%

    No Known Activations