© 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. 36-GEMMASCOPE-RES-16K
    6. 7284
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal conclusions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoresizingMask
    -0.47
    !*\
    -0.43
     ModelExpression
    -0.43
    出版年
    -0.42
    errHandler
    -0.40
    <?,
    -0.38
    DataPropertyName
    -0.37
    windowFixed
    -0.37
    Biografía
    -0.36
    ghold
    -0.36
    POSITIVE LOGITS
     above
    3.72
    above
    3.23
    Above
    2.89
     Above
    2.83
     acima
    2.72
     ABOVE
    2.58
     aforementioned
    2.50
     выше
    2.36
    上述
    2.28
     aforesaid
    2.23
    Activations Density 2.328%

    No Known Activations