© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5271
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their associated contexts in quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences ending with conjunctions

    np_acts-logits-general · gemini-2.0-flash

    and, so, but, which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inoltre
    -0.67
     however
    -0.62
    此外
    -0.61
     além
    -0.61
     tuttavia
    -0.60
     cependant
    -0.58
     besides
    -0.56
    なお
    -0.52
    however
    -0.52
     Ayrıca
    -0.51
    POSITIVE LOGITS
     And
    2.35
    And
    1.86
     Và
    1.22
     and
    1.18
     So
    1.12
     AND
    1.11
     Which
    1.05
     và
    0.98
    Which
    0.97
     But
    0.96
    Activations Density 0.245%

    No Known Activations