Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 7617
    Prev
    Next
    INDEX
    Explanations

    instances of game scores and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -1.01
    RegressionTest
    -0.96
    ⓧ
    -0.81
    NameInMap
    -0.72
     يتيمه
    -0.70
    __*/
    -0.69
     للاسماء
    -0.67
    libft
    -0.67
    PerformLayout
    -0.65
    thâu
    -0.65
    POSITIVE LOGITS
    heit
    0.42
    })->
    0.40
    point
    0.39
     point
    0.39
     points
    0.38
     pointed
    0.37
    Viewing
    0.37
    quinha
    0.37
     sessão
    0.36
     run
    0.36
    Activations Density 0.094%

    No Known Activations