© 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. 40-GEMMASCOPE-RES-16K
    6. 5130
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols used in equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -0.66
     PeEnEo
    -0.66
     informée
    -0.66
     koszulka
    -0.65
     ujednoznacz
    -0.65
     internetowa
    -0.62
     Réponses
    -0.62
     Fallon
    -0.61
     hébergement
    -0.61
     miniaturka
    -0.60
    POSITIVE LOGITS
    bibfield
    0.64
    bibinfo
    0.45
     يتيمه
    0.38
    citenamefont
    0.37
    }{*}{}
    0.34
    Pyx
    0.32
    tfrac
    0.32
    hdashline
    0.32
     ioutil
    0.30
    hfill
    0.29
    Activations Density 0.300%

    No Known Activations