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

    Neuronpedia

    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. 16-GEMMASCOPE-RES-16K
    11. 2788
    Prev
    Next
    INDEX
    Explanations

    technical references related to software or programming concepts

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    evocative nouns and adjectives

    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
    出版年
    -0.72
     uſe
    -0.66
     chofe
    -0.65
     juſt
    -0.63
     uſed
    -0.62
     purpoſe
    -0.62
     juſ
    -0.61
     ſee
    -0.60
     juist
    -0.60
     poffible
    -0.60
    POSITIVE LOGITS
     glorious
    0.86
    bkz
    0.79
     unholy
    0.77
     mighty
    0.72
     hapless
    0.71
     glory
    0.71
    tagHelperRunner
    0.69
     evil
    0.67
    Behold
    0.67
    Alas
    0.63
    Activations Density 0.724%

    No Known Activations