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. 20-GEMMASCOPE-RES-16K
    6. 10994
    Prev
    Next
    INDEX
    Explanations

    references to scientific theories and concepts related to physics

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

    Tokens following and, by, or a period

    np_acts-logits-general · gemini-2.0-flash

    scientific attributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urlpatterns
    -0.62
    劲
    -0.48
    Autoritní
    -0.47
    similiano
    -0.44
    essoas
    -0.43
    Organisateur
    -0.43
    })->
    -0.43
    )?;
    -0.42
     paysage
    -0.42
     compositional
    -0.42
    POSITIVE LOGITS
    enderror
    0.69
     InputDecoration
    0.69
     يتيمه
    0.68
    ArrowToggle
    0.68
    GIH
    0.64
    :✨
    0.64
    UPAC
    0.64
     Мексичка
    0.63
    OGND
    0.63
    liesslich
    0.62
    Activations Density 0.477%

    No Known Activations