© 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. 10-GEMMASCOPE-RES-16K
    6. 7977
    Prev
    Next
    INDEX
    Explanations

    connective phrases and words that introduce consequences or elaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abstractmethod
    -0.57
    ellido
    -0.56
    stdc
    -0.54
     JpaRepository
    -0.54
     SafeMath
    -0.54
    endwhile
    -0.53
    出版年
    -0.53
    ロウィン
    -0.53
     endwhile
    -0.53
    Rüyada
    -0.52
    POSITIVE LOGITS
     internetowa
    0.35
     esprits
    0.32
     platí
    0.30
     olyan
    0.30
     couverts
    0.29
    GIVEREF
    0.29
     kuni
    0.29
    aduras
    0.29
    ที่มี
    0.28
     like
    0.28
    Activations Density 0.475%

    No Known Activations