© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9731
    Prev
    Next
    INDEX
    Explanations

    elements related to legal and ethical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.54
     transférez
    -0.53
    SharedDtor
    -0.45
    SequentialGroup
    -0.43
    jspb
    -0.42
     roba
    -0.42
    PropertyChanging
    -0.40
    Kanpo
    -0.39
    Personendaten
    -0.39
     validamos
    -0.39
    POSITIVE LOGITS
     Paglinawan
    0.71
    mybatisplus
    0.66
    Obrázky
    0.61
    oredCriteria
    0.59
    AutoField
    0.57
     NSCoder
    0.56
    ChildScrollView
    0.54
    hyrchwyd
    0.54
     hObject
    0.54
    invokeLater
    0.51
    Activations Density 0.377%

    No Known Activations