© 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. 27-GEMMASCOPE-RES-16K
    11. 8457
    Prev
    Next
    INDEX
    Explanations

    relations and conditions affecting systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    timmung
    -0.36
    しま
    -0.35
    ußer
    -0.35
     manages
    -0.33
     estre
    -0.33
     tärke
    -0.33
     ARS
    -0.33
     Exhibition
    -0.33
     поддержа
    -0.32
    ulement
    -0.32
    POSITIVE LOGITS
    tonode
    0.65
     demek
    0.64
     conclude
    0.62
     conclure
    0.54
     значит
    0.54
     propOrder
    0.53
     conclusion
    0.52
     concluded
    0.52
     suspect
    0.50
    conclusion
    0.49
    Activations Density 0.615%

    No Known Activations