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. 3-GEMMASCOPE-RES-16K
    6. 10213
    Prev
    Next
    INDEX
    Explanations

    words related to specific brands and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.72
     *__
    -0.70
    queryInterface
    -0.70
    __*/
    -0.67
     XCTest
    -0.65
    脚注の使い方
    -0.64
    ---*/
    -0.63
     Kono
    -0.59
     FormsModule
    -0.58
    AddHtmlAttribute
    -0.57
    POSITIVE LOGITS
     Cag
    1.29
    ug
    1.27
    UG
    1.24
     SAG
    1.24
    sg
    1.24
     Kag
    1.21
     cg
    1.20
    gg
    1.20
    TAG
    1.18
    agg
    1.18
    Activations Density 1.428%

    No Known Activations