© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 9489
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating emotional or rhetorical emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     while
    -0.67
     although
    -0.64
     due
    -0.62
     since
    -0.62
    由于
    -0.57
    ながら
    -0.55
     despite
    -0.53
     whilst
    -0.53
     prior
    -0.50
     поскольку
    -0.50
    POSITIVE LOGITS
     And
    1.27
    And
    1.04
     Which
    0.88
     Especially
    0.82
    Which
    0.77
    Especially
    0.77
     Or
    0.75
     Maybe
    0.74
     Oh
    0.74
     Sort
    0.74
    Activations Density 0.480%

    No Known Activations