© 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. 20-GEMMASCOPE-RES-16K
    11. 15045
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and legal processes

    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
    extAlignment
    -0.59
     invokingState
    -0.57
    forChild
    -0.50
    manuel
    -0.47
     NIS
    -0.47
    libft
    -0.47
     Else
    -0.47
    ▾
    -0.46
    yelitis
    -0.46
    \{\\
    -0.46
    POSITIVE LOGITS
     and
    0.69
     &
    0.66
    /
    0.66
    ＆
    0.50
    XmlAccessType
    0.48
     \&
    0.47
     nordrhein
    0.46
    ParallelGroup
    0.46
     Expédié
    0.45
    OGND
    0.45
    Activations Density 1.352%

    No Known Activations