© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15284
    Prev
    Next
    INDEX
    Explanations

    constructs related to documentation and annotations within code or scientific writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Captions, figure legends, and descriptions

    np_acts-logits-general · gemini-2.0-flash

    captions, descriptions, or legends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.78
    DeleteBehavior
    -0.69
    InvalidProtocol
    -0.67
     resourceCulture
    -0.65
    цездатний
    -0.59
    expandindo
    -0.56
     CreateTagHelper
    -0.56
    脚注の使い方
    -0.56
    GraphicsUnit
    -0.55
    urlpatterns
    -0.53
    POSITIVE LOGITS
     caption
    1.77
     captions
    1.61
    caption
    1.51
     description
    1.45
     Caption
    1.42
     descriptions
    1.30
    Caption
    1.29
     captioned
    1.25
     Captions
    1.25
    description
    1.23
    Activations Density 0.711%

    No Known Activations