© 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 EvalsExportsAPI 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. 6335
    Prev
    Next
    INDEX
    Explanations

    phrases indicating complexity, contrast, and nuanced perspectives

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

    after commas (,) and before conjunctions

    np_acts-logits-general · gemini-2.0-flash

    commas preceding words

    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
    parsedMessage
    -0.82
    both
    -0.78
    either
    -0.76
     समीक्षाओं
    -0.70
     CreateTagHelper
    -0.68
     незавершена
    -0.67
    цездатний
    -0.66
     either
    -0.64
     its
    -0.63
    seamnă
    -0.63
    POSITIVE LOGITS
     yet
    1.01
     albeit
    0.81
     Yet
    0.76
    yet
    0.76
     often
    0.70
     sometimes
    0.69
    Yet
    0.68
    albeit
    0.68
     YET
    0.62
     oftentimes
    0.60
    Activations Density 0.190%

    No Known Activations