© 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. 15-GEMMASCOPE-RES-16K
    6. 1008
    Prev
    Next
    INDEX
    Explanations

    structured data or references related to academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RuleContext
    -0.39
    ocardial
    -0.39
     ابت
    -0.38
    盡
    -0.38
    fär
    -0.36
    vents
    -0.35
     Dye
    -0.35
     closing
    -0.35
     selfie
    -0.35
     kokona
    -0.34
    POSITIVE LOGITS
     ISSN
    0.74
    ViewImports
    0.71
    ISSN
    0.69
    NameInMap
    0.66
    fjspx
    0.64
    DIPSETTING
    0.60
     arşivlendi
    0.60
    Personensuche
    0.59
    principalColumn
    0.57
     OFDb
    0.57
    Activations Density 0.224%

    No Known Activations