© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8801
    Prev
    Next
    INDEX
    Explanations

    patterns in code and technical syntax related to expressions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Liefs
    -0.37
     vieles
    -0.37
    ękuję
    -0.36
     Turquía
    -0.35
     sûr
    -0.33
     Gestión
    -0.33
    Продам
    -0.32
     Jurí
    -0.32
    shame
    -0.32
     econó
    -0.32
    POSITIVE LOGITS
    mybatisplus
    0.73
     للاسماء
    0.67
    DataAnnotations
    0.66
     <<<<<<<<<<<<<<
    0.63
    Życiorys
    0.62
    fortawesome
    0.61
     سكانية
    0.61
    antiation
    0.60
    +#+
    0.60
     ArrayAdapter
    0.60
    Activations Density 2.194%

    No Known Activations