© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7877
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the token "Sp," which may indicate a focus on certain characters or entities within the text

    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
     ſeveral
    -1.01
     Monfieur
    -1.00
     myſelf
    -0.98
     whoſe
    -0.95
     Theſe
    -0.93
     againſt
    -0.91
     purpoſe
    -0.90
     himſelf
    -0.90
     ſever
    -0.89
     Efq
    -0.88
    POSITIVE LOGITS
     Sp
    1.52
    Sp
    1.41
     sp
    1.40
    sp
    1.12
     Spo
    0.98
     spo
    0.98
     SPO
    0.92
     SP
    0.90
    spo
    0.89
    Spo
    0.84
    Activations Density 0.061%

    No Known Activations