© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4736
    Prev
    Next
    INDEX
    Explanations

    specific phrases or terminology related to physical processing and manufacturing techniques

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

    that come before adverbs or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    adverbs or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.80
     
    -0.58
    ньше
    -0.58
    except
    -0.55
    我了
    -0.54
    嬉しいです
    -0.52
    GEBURTSDATUM
    -0.52
     called
    -0.50
     защото
    -0.50
    他要
    -0.49
    POSITIVE LOGITS
    apimachinery
    1.05
     arşivlendi
    0.94
     oftentimes
    0.90
     resourceCulture
    0.84
     nemlig
    0.84
     whatsoever
    0.83
    soever
    0.80
     wszel
    0.79
     ciertamente
    0.79
     весьма
    0.79
    Activations Density 2.589%

    No Known Activations