© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 16381
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical data and comparisons in various contexts

    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
    FunctionFlags
    -0.47
    UnsafeEnabled
    -0.46
    rido
    -0.43
    DrawerToggle
    -0.41
    MenuInflater
    -0.40
    друг
    -0.39
    couvrez
    -0.38
    ChildScrollView
    -0.38
     bure
    -0.37
    RTLR
    -0.37
    POSITIVE LOGITS
     stay
    3.73
    stay
    3.44
     stayed
    3.34
     Stay
    3.31
     stays
    3.30
    Stay
    3.20
     staying
    3.13
     STAY
    3.06
    STAY
    2.91
     Stays
    2.66
    Activations Density 0.608%

    No Known Activations