© 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. 2153
    Prev
    Next
    INDEX
    Explanations

    connections between cultural elements and scholarly studies

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

    Characters in file paths and code

    np_acts-logits-general · gemini-2.0-flash

    links with code or identifiers

    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
    GEBURTSDATUM
    -1.13
    oredCriteria
    -0.79
     protoimpl
    -0.70
    tagHelperRunner
    -0.70
     الاطلاع
    -0.66
    AndEndTag
    -0.66
     '\\;'
    -0.65
    fjspx
    -0.65
    addCriterion
    -0.62
     OFDb
    -0.62
    POSITIVE LOGITS
     Drapeau
    0.51
     oriental
    0.48
     wester
    0.47
    Filmografie
    0.47
     Reels
    0.46
    forChild
    0.46
    aguya
    0.44
     Pavia
    0.44
     fascism
    0.44
     /\.(
    0.44
    Activations Density 0.250%

    No Known Activations