© 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. 36-GEMMASCOPE-RES-16K
    6. 8129
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate enabling or allowing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.54
    wantErr
    -0.47
     initComponents
    -0.47
     informée
    -0.46
    ostante
    -0.44
     disambiguazione
    -0.44
    发表于
    -0.43
    #+#
    -0.43
     تكبرها
    -0.42
     provoquer
    -0.42
    POSITIVE LOGITS
     easily
    1.00
    easily
    0.90
     facilement
    0.85
     facilmente
    0.77
     freely
    0.75
     fácilmente
    0.73
     Easily
    0.69
     safely
    0.69
    Easily
    0.68
     confidently
    0.67
    Activations Density 0.445%

    No Known Activations