© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10267
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to significant characters or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.58
    toppers
    -0.56
     Thorpe
    -0.54
    anzug
    -0.54
    stdc
    -0.54
    sunshine
    -0.53
     Culver
    -0.52
    ″]
    -0.52
     kentang
    -0.52
     časti
    -0.50
    POSITIVE LOGITS
    kin
    0.99
     cin
    0.93
    KIN
    0.92
     Kin
    0.88
     kin
    0.82
     KIN
    0.81
    Kin
    0.78
     Cin
    0.78
     Scarlet
    0.77
    nin
    0.73
    Activations Density 0.032%

    No Known Activations