© 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 - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14607
    Prev
    Next
    INDEX
    Explanations

    complex mathematical constructs and conditions related to matrices and parameters

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

    appearing with "and" or "or"

    np_acts-logits-general · gemini-2.0-flash

    either...or, both, respectively

    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
    WEBPACK
    -0.72
    .~(\
    -0.68
    ("/")
    -0.62
     $("<
    -0.60
    ("//
    -0.59
    }{|
    -0.59
    átky
    -0.59
    ">{{
    -0.59
     Polis
    -0.57
    ://"
    -0.56
    POSITIVE LOGITS
     either
    0.90
    either
    0.85
    respectively
    0.82
     both
    0.75
     respectivement
    0.75
     suivants
    0.72
    both
    0.71
     respectively
    0.70
     lastly
    0.68
     Either
    0.67
    Activations Density 1.017%

    No Known Activations