© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7795
    Prev
    Next
    INDEX
    Explanations

    tokens related to coding syntax and structure

    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
    ſelf
    -0.65
    Personendaten
    -0.58
    ValueStyle
    -0.58
    XmlAccessType
    -0.56
    出版年
    -0.54
    ſelves
    -0.53
     ſch
    -0.51
     Monfieur
    -0.51
     jadx
    -0.50
     autorytatywna
    -0.49
    POSITIVE LOGITS
    andExpect
    0.44
    QMetaType
    0.40
     Connectez
    0.39
    enterian
    0.39
    iffer
    0.37
    otras
    0.36
     아니라
    0.35
     Oester
    0.35
    olahan
    0.34
     zainteres
    0.34
    Activations Density 0.563%

    No Known Activations