© 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. 3-GEMMASCOPE-RES-16K
    11. 9492
    Prev
    Next
    INDEX
    Explanations

    phrases that contain contractions or possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TreeSet
    -0.38
    __.__
    -0.33
     ¦
    -0.32
     Skyl
    -0.30
     Â
    -0.30
     .:
    -0.30
    inflater
    -0.30
    tagHelperRunner
    -0.29
     comp
    -0.29
    ――
    -0.29
    POSITIVE LOGITS
    adaptiveStyles
    0.58
    出版年
    0.57
    UnusedPrivate
    0.55
     OFDb
    0.52
    Jereo
    0.52
     defaultstate
    0.52
     llorar
    0.52
    routeProvider
    0.49
     surla
    0.48
     désactiv
    0.48
    Activations Density 0.124%

    No Known Activations