© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9721
    Prev
    Next
    INDEX
    Explanations

    keywords associated with technical components and specifications

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

    Follows hyphens, math symbols, or is punctuation

    np_acts-logits-general · gemini-2.0-flash

    right-hand side

    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
     
    -0.53
     ģ
    -0.52
    ждую
    -0.46
     recensement
    -0.46
     ...
    -0.45
     وتسجيلات
    -0.45
     lanjut
    -0.45
    ställning
    -0.45
     palmas
    -0.44
    šek
    -0.44
    POSITIVE LOGITS
    withstanding
    0.93
    NUMX
    0.90
    CrossRef
    0.76
    HasAnnotation
    0.75
    yntaxException
    0.73
    ValueGeneration
    0.71
    WebVitals
    0.71
    etheless
    0.71
    BASEPATH
    0.69
    viembre
    0.67
    Activations Density 1.163%

    No Known Activations