© 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. 34-GEMMASCOPE-RES-16K
    11. 12974
    Prev
    Next
    INDEX
    Explanations

    references to personal identity and cultural expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.80
    verwijspagina
    -0.76
    expandindo
    -0.75
     ujednoznacz
    -0.73
    脚注の使い方
    -0.73
     Biôgrafia
    -0.72
     disambiguazione
    -0.68
     '\\;'
    -0.68
     defaultstate
    -0.67
     Administrativna
    -0.67
    POSITIVE LOGITS
     financeira
    0.51
     aikaa
    0.49
     głowy
    0.44
    eluarkan
    0.43
     telinga
    0.43
     gracia
    0.42
     isolado
    0.42
     blessé
    0.42
     isolé
    0.41
     parça
    0.41
    Activations Density 0.020%

    No Known Activations