© 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. 31-GEMMASCOPE-RES-16K
    11. 5377
    Prev
    Next
    INDEX
    Explanations

    connections to emerging artists and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    emerging and young talented artists or performers being showcased or developed.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.49
    UserScript
    -0.49
    GTCX
    -0.45
     wireType
    -0.44
    новништво
    -0.44
     citrate
    -0.43
     bağlantılar
    -0.41
     OFDb
    -0.41
     emptied
    -0.41
    unknownFields
    -0.38
    POSITIVE LOGITS
     talent
    1.77
     talented
    1.69
     talents
    1.62
     talento
    1.56
     talentos
    1.50
    talent
    1.43
     талан
    1.41
    Talent
    1.27
     Talent
    1.27
     Talents
    1.20
    Activations Density 0.310%

    No Known Activations