© 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. 7750
    Prev
    Next
    INDEX
    Explanations

    instances of programming-related actions and errors

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

    subjective personal pronouns and their associated verbs in first and second person contexts.

    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
     sağlar
    -0.33
     gerekir
    -0.30
     مس
    -0.29
     принадлежа
    -0.28
    くれた
    -0.27
     proxim
    -0.26
    TIC
    -0.26
     относи
    -0.26
     s
    -0.25
     eventually
    -0.25
    POSITIVE LOGITS
     đang
    1.47
    正在
    1.27
     sedang
    1.25
     stiamo
    1.22
    กำลัง
    1.15
     stanno
    1.06
     estamos
    1.03
     Estamos
    0.96
     estás
    0.93
     estoy
    0.89
    Activations Density 1.246%

    No Known Activations