© 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. 10-GEMMASCOPE-RES-16K
    11. 1951
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and its variations, indicating it is focused on definite articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viitteet
    -0.61
    紹介します
    -0.59
    uasion
    -0.59
    enzie
    -0.58
    Affirmed
    -0.56
    autogui
    -0.54
     Walkover
    -0.54
    jetty
    -0.53
    最快更新
    -0.53
    ograp
    -0.53
    POSITIVE LOGITS
     midst
    1.21
     وفي
    0.86
     vicinity
    0.86
    inthe
    0.83
    InThe
    0.83
     וב
    0.80
    dalam
    0.80
    Portale
    0.78
     Dalam
    0.76
    ท้าย
    0.76
    Activations Density 0.402%

    No Known Activations