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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 3253
    Prev
    Next
    INDEX
    Explanations

    specific biological terms and their associated data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.82
    PerformLayout
    -0.77
     XCTest
    -0.77
    ---*/
    -0.75
    Diwedd
    -0.70
     *__
    -0.68
     Dostupné
    -0.67
     FormsModule
    -0.67
     Xunit
    -0.66
    Converse
    -0.65
    POSITIVE LOGITS
    ig
    1.10
    ggg
    1.10
     Cag
    1.10
    gg
    1.09
    ag
    1.08
     Kag
    1.08
    gag
    1.07
    ug
    1.04
    ging
    1.04
     Wag
    1.03
    Activations Density 1.179%

    No Known Activations