© 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. 11353
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to labeling and naming, as well as discussions of identity and characterization

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

    followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    calling and characterizing actions

    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
     ويكيميديا
    -0.55
     electrico
    -0.52
    resave
    -0.51
    -0.50
     yine
    -0.49
    /−
    -0.48
     Endlich
    -0.47
     Públicas
    -0.47
     extradition
    -0.47
     Exactos
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.75
    setVerticalGroup
    0.74
     it
    0.74
     them
    0.70
     ivelany
    0.69
     defaultstate
    0.68
    IMPORTED
    0.67
     themselves
    0.66
    makeText
    0.66
     ourselves
    0.66
    Activations Density 0.325%

    No Known Activations