© 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. 125396
    Prev
    Next
    INDEX
    Explanations

    numerical formatting or identification tags, particularly those related to references or citations

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

    attribution by author or entity

    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
    tagHelperRunner
    -0.65
    ніципалі
    -0.58
    ReusableCell
    -0.56
     CreateTagHelper
    -0.54
     فريبيس
    -0.54
    AndEndTag
    -0.53
    CloseOperation
    -0.51
    ConstraintMaker
    -0.50
    ագրություններ
    -0.50
     creș
    -0.48
    POSITIVE LOGITS
    UpdatedBy
    0.63
     createdBy
    0.57
     by
    0.54
     By
    0.53
     AssemblyCompany
    0.52
    by
    0.52
    By
    0.52
    CreatedBy
    0.48
     BY
    0.45
    ByUser
    0.45
    Activations Density 0.025%

    No Known Activations