© 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. 3253
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific terms, particularly those related to functions or variables in algebra and other mathematical expressions

    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
    __*/
    -0.81
     XCTest
    -0.77
    ---*/
    -0.77
     FormsModule
    -0.76
    PerformLayout
    -0.73
    Diwedd
    -0.69
    mandu
    -0.68
     *__
    -0.67
    ymce
    -0.66
    Converse
    -0.65
    POSITIVE LOGITS
    ging
    1.10
    gg
    1.10
    gag
    1.10
    ggg
    1.08
     Kag
    1.08
    ag
    1.06
    ig
    1.05
     Cag
    1.04
    sg
    1.03
     Pg
    1.03
    Activations Density 1.368%

    No Known Activations