© 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. 10-GEMMASCOPE-RES-16K
    6. 11023
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions, requests, or discussions related to products and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttemberg
    -0.49
    :✨
    -0.48
    VersionUID
    -0.41
     maș
    -0.41
    ſelves
    -0.41
     متحده
    -0.40
    IsUnicode
    -0.39
    SPATH
    -0.38
    StructEnd
    -0.38
    SubMenu
    -0.38
    POSITIVE LOGITS
     coloured
    0.58
    ագրություններ
    0.57
    цездатний
    0.56
     loosing
    0.54
     colour
    0.54
     didalam
    0.54
     COLOUR
    0.53
    脚注の使い方
    0.52
    Neighbour
    0.51
     Caw
    0.50
    Activations Density 1.343%

    No Known Activations