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. 2-GEMMASCOPE-RES-16K
    6. 6157
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups indicated by the word "whom."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recently
    -0.56
     perd
    -0.53
    Nevermind
    -0.51
    ona
    -0.50
     especially
    -0.49
     Ки
    -0.48
    ings
    -0.48
    INGS
    -0.46
    ))$.
    -0.46
     بلند
    -0.45
    POSITIVE LOGITS
     مرئيه
    0.98
    OGND
    0.97
     חיצוניים
    0.95
    Geplaatst
    0.86
     للاسماء
    0.86
     StatefulWidget
    0.85
    aarrggbb
    0.84
     يتيمه
    0.83
    whom
    0.81
     TextInputType
    0.81
    Activations Density 0.060%

    No Known Activations