© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 6361
    Prev
    Next
    INDEX
    Explanations

    phrases that involve function calls and method invocations in programming contexts

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

    Comes after certain prepositions

    np_acts-logits-general · gemini-2.0-flash

    technical jargon and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     are
    -0.34
     lisäksi
    -0.33
     any
    -0.31
     thiệu
    -0.31
     Könige
    -0.31
     an
    -0.30
     Schwier
    -0.29
     christlichen
    -0.29
     the
    -0.28
     Kreise
    -0.28
    POSITIVE LOGITS
    әрмәләр
    0.77
    ésult
    0.71
    MessageOf
    0.71
     betweenstory
    0.71
    請繼續往下閱讀
    0.71
    IndentedString
    0.66
    Дереккөздер
    0.64
    Билгалдахарш
    0.64
     nakalista
    0.64
     mergeFrom
    0.63
    Activations Density 0.212%

    No Known Activations