© 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. 39-GEMMASCOPE-RES-16K
    11. 6
    Prev
    Next
    INDEX
    Explanations

    references to significant literary works or historical texts

    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
     muchacha
    -0.50
     Stirn
    -0.46
     idéia
    -0.44
    sphase
    -0.44
     boneca
    -0.43
     Sicher
    -0.43
     Aktivitäten
    -0.43
     Ambiental
    -0.42
    wußt
    -0.42
     tertulis
    -0.42
    POSITIVE LOGITS
    createServer
    0.46
     pops
    0.44
     tackled
    0.44
     defStyleAttr
    0.44
     ramos
    0.42
     tackle
    0.41
     tackling
    0.41
     synchron
    0.41
    posure
    0.40
    postmedia
    0.40
    Activations Density 0.294%

    No Known Activations