© 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. 2802
    Prev
    Next
    INDEX
    Explanations

    references to data values and statistical representations in research contexts

    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
    MessageTagHelper
    -0.64
    ItemBackground
    -0.61
     CallOverrides
    -0.59
     utafitiHapana
    -0.59
    oa̍t
    -0.57
    Aholisi
    -0.56
     transfieras
    -0.55
    ьаж
    -0.53
    hyrchwyd
    -0.52
    цездатний
    -0.50
    POSITIVE LOGITS
     informée
    0.40
    swick
    0.38
    PerformLayout
    0.38
    dersfield
    0.34
    PLIC
    0.33
    makeConstraints
    0.33
    schedulers
    0.32
    kheim
    0.32
    makeText
    0.32
    labelledby
    0.31
    Activations Density 0.613%

    No Known Activations