© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 9838
    Prev
    Next
    INDEX
    Explanations

    functions and operations related to data structures and queries in programming

    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
     read
    -0.28
     las
    -0.27
     import
    -0.27
     student
    -0.26
     next
    -0.26
     yh
    -0.25
     save
    -0.25
    킴
    -0.25
     go
    -0.24
     if
    -0.24
    POSITIVE LOGITS
    脚注の使い方
    0.81
     bezeichneter
    0.76
    msgTypes
    0.75
     Paglinawan
    0.75
    OGND
    0.75
     StringTokenizer
    0.75
    IVEREF
    0.67
     становника
    0.67
    thâu
    0.66
    WithMany
    0.66
    Activations Density 0.254%

    No Known Activations