© 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. 58052
    Prev
    Next
    INDEX
    Explanations

    references to inclusive language and examples

    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
    rs
    -0.52
    だけ
    -0.50
    only
    -0.47
    stdlib
    -0.45
    tri
    -0.43
    kna
    -0.43
    bc
    -0.43
    art
    -0.43
     Wei
    -0.42
     only
    -0.42
    POSITIVE LOGITS
     Including
    1.18
    Including
    1.17
    INCLUDING
    1.09
    including
    1.06
     including
    1.06
    Includes
    1.02
     incluindo
    1.02
     einschließlich
    0.99
     incluyendo
    0.98
     INCLUDING
    0.97
    Activations Density 0.045%

    No Known Activations