© 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. 0-GEMMASCOPE-RES-16K
    11. 11235
    Prev
    Next
    INDEX
    Explanations

    references to external elements or factors affecting systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hyö
    -0.41
     läßt
    -0.40
     kysy
    -0.38
    Outside
    -0.38
    állítás
    -0.38
     plaît
    -0.37
     näin
    -0.36
    醐
    -0.36
     abroad
    -0.36
    anskje
    -0.35
    POSITIVE LOGITS
     external
    1.99
     External
    1.64
     internal
    1.56
    external
    1.50
     EXTERNAL
    1.46
     externally
    1.42
    External
    1.38
     externe
    1.22
     internally
    1.22
     Internal
    1.20
    Activations Density 0.224%

    No Known Activations