© 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. 7962
    Prev
    Next
    INDEX
    Explanations

    formatted structures related to personal identification information

    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
     lenker
    -0.59
    oa̍t
    -0.43
    ///</
    -0.43
    IntoConstraints
    -0.42
     Administrativna
    -0.40
     مشين
    -0.39
    Hochspringen
    -0.39
     OFDb
    -0.37
     называется
    -0.36
     podjela
    -0.35
    POSITIVE LOGITS
     surname
    1.23
     surnames
    1.03
    surname
    1.00
    Surname
    0.99
     Surname
    0.98
    lastname
    0.91
    姓
    0.91
     LastName
    0.91
     lastname
    0.90
    LastName
    0.87
    Activations Density 0.186%

    No Known Activations