© 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. 31-GEMMASCOPE-RES-16K
    11. 1265
    Prev
    Next
    INDEX
    Explanations

    Arabic words and phrases related to preference and selection

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

    non-Latin script characters, particularly Arabic and Unicode escape sequences.

    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
     ſch
    -0.80
     pleaſure
    -0.80
     ſta
    -0.77
     ſche
    -0.75
     houſe
    -0.74
     ſte
    -0.72
     verſ
    -0.69
     ligiloj
    -0.68
     abſ
    -0.67
     juſ
    -0.66
    POSITIVE LOGITS
     emprego
    0.41
     Técnica
    0.38
     Administração
    0.37
     Ensino
    0.36
     boneco
    0.36
     níveis
    0.36
     Estadual
    0.35
     Segurança
    0.35
     avancée
    0.34
     inversión
    0.33
    Activations Density 0.009%

    No Known Activations