© 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. 13275
    Prev
    Next
    INDEX
    Explanations

    numeric references and citations typically found in academic papers

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

    journal volumes or article numbers

    np_acts-logits-general · gemini-2.0-flash

    years in parentheses

    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
    AsUp
    -0.64
    __':
    -0.60
    messageInfo
    -0.60
     الحره
    -0.60
    données
    -0.57
    ंदीखरीदारी
    -0.54
     ModelExpression
    -0.52
     jScrollPane
    -0.52
    UrlResolution
    -0.52
     snippetHide
    -0.51
    POSITIVE LOGITS
    GLenum
    0.56
    liquez
    0.55
     resourceCulture
    0.52
    henswürdigkeiten
    0.47
    TagHelper
    0.47
    parian
    0.46
    loroethane
    0.46
     yore
    0.45
     hObject
    0.45
    thias
    0.45
    Activations Density 0.107%

    No Known Activations