© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 16056
    Prev
    Next
    INDEX
    Explanations

    questions about methods or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schulte
    -0.89
     Münch
    -0.82
     raft
    -0.77
    BASEPATH
    -0.74
     Milne
    -0.73
    BrowserModule
    -0.73
    CID
    -0.71
     AE
    -0.69
    iku
    -0.69
    picasso
    -0.68
    POSITIVE LOGITS
     how
    1.92
     How
    1.63
     HOW
    1.59
    How
    1.52
    HOW
    1.36
    how
    1.30
    יצד
    1.05
     Howell
    1.05
     Howe
    1.05
    howto
    0.99
    Activations Density 0.040%

    No Known Activations