© 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. 24-GEMMASCOPE-RES-16K
    11. 11951
    Prev
    Next
    INDEX
    Explanations

    expressions related to appreciation and gratitude in social contexts

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

    following prepositions or nouns

    np_acts-logits-general · gemini-2.0-flash

    oil and gas conversion windows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.50
    DispatchToProps
    -0.42
    noons
    -0.42
    URIComponent
    -0.41
    OGND
    -0.41
    transQ
    -0.40
     jspb
    -0.39
    {}/
    -0.39
    UVWXYZ
    -0.38
    ;*/
    -0.38
    POSITIVE LOGITS
     There
    1.58
     This
    1.52
     These
    1.51
     They
    1.45
     The
    1.40
     We
    1.33
     However
    1.31
     When
    1.31
     It
    1.31
     If
    1.30
    Activations Density 3.495%

    No Known Activations