© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 118003
    Prev
    Next
    INDEX
    Explanations

    elements related to procedural and editorial updates or issues

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

    matters, issues, maintenance, improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |$
    -0.40
     complete
    -0.40
    __(/*!
    -0.39
     MEC
    -0.39
    PhysRevD
    -0.35
     Cune
    -0.35
    jspb
    -0.35
    ->___
    -0.35
     оригіналу
    -0.34
     кӀош
    -0.34
    POSITIVE LOGITS
    dafx
    0.78
     betweenstory
    0.60
     InputDecoration
    0.58
    cellaneous
    0.57
    mybatisplus
    0.54
     pérd
    0.53
    administrative
    0.53
     réflex
    0.51
     cuestiones
    0.51
     فريبيس
    0.50
    Activations Density 0.121%

    No Known Activations