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

    Neuronpedia

    Jacobian LensNEW
    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. 14-GEMMASCOPE-RES-16K
    11. 10287
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to legal or contractual obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    majánló
    -0.96
     Monfieur
    -0.94
     queſta
    -0.86
     myſelf
    -0.86
     Eſ
    -0.85
     Reſ
    -0.82
     itſelf
    -0.82
    Personensuche
    -0.82
     Diſ
    -0.80
     indígen
    -0.78
    POSITIVE LOGITS
    ↵↵
    0.40
     de
    0.39
    ,
    0.38
    <eos>
    0.36
     in
    0.33
     (
    0.33
     of
    0.32
     men
    0.31
     mar
    0.31
    ↵
    0.30
    Activations Density 0.254%

    No Known Activations