© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 7300
    Prev
    Next
    INDEX
    Explanations

    descriptions of vehicle design and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jaringan
    -0.36
    pecabezas
    -0.31
    fangen
    -0.30
     âmes
    -0.30
     nœ
    -0.30
     yüzük
    -0.30
    Counter
    -0.30
     dis
    -0.30
     sendi
    -0.30
     helse
    -0.30
    POSITIVE LOGITS
     AssemblyCulture
    0.73
     disambiguazione
    0.66
     EconPapers
    0.66
     bonnet
    0.63
     repaint
    0.63
     decals
    0.62
     hood
    0.61
     spoiler
    0.60
    脚注の使い方
    0.60
     esternos
    0.60
    Activations Density 0.138%

    No Known Activations