© 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. 39-GEMMASCOPE-RES-16K
    11. 2807
    Prev
    Next
    INDEX
    Explanations

    references to recognition or awards in the context of television or film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Derbyniad
    -0.46
    amssymb
    -0.44
    الحياه
    -0.44
    تقاوى
    -0.42
     дописавши
    -0.38
    Geplaatst
    -0.38
    delwed
    -0.38
    RTEX
    -0.35
    ſelves
    -0.35
    GOTREF
    -0.35
    POSITIVE LOGITS
     direc
    2.55
     director
    2.55
     direction
    2.53
     Dire
    2.50
     dir
    2.48
     Dir
    2.45
     directing
    2.42
     Direction
    2.41
     directors
    2.39
    Dire
    2.38
    Activations Density 1.433%

    No Known Activations