© 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. 18-GEMMASCOPE-RES-16K
    11. 9004
    Prev
    Next
    INDEX
    Explanations

    sections of text with non-zero activation values, indicating a lack of relevant content

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

    Immediately follows a comma

    np_acts-logits-general · gemini-2.0-flash

    medical terms and measurements

    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
    ēju
    -0.44
    Seeder
    -0.42
    ميل
    -0.41
    aaaaaaaa
    -0.41
     gesti
    -0.41
    Coll
    -0.40
    RunAsync
    -0.40
    dan
    -0.39
     trå
    -0.39
     coa
    -0.38
    POSITIVE LOGITS
    
    0.89
     дописавши
    0.87
    tvguidetime
    0.74
     تانيه
    0.70
    SPATH
    0.68
    kuuta
    0.66
     الرياضيه
    0.66
    devamını
    0.64
    annica
    0.63
    $_['
    0.63
    Activations Density 0.032%

    No Known Activations