© 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. 9874
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions indicating small amounts of time

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

    "few" followed by a unit of time

    np_acts-logits-general · gemini-2.0-flash

    few units of time

    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
    mantec
    -0.52
    vání
    -0.51
     totales
    -0.47
    bridi
    -0.47
     suatu
    -0.46
     alguna
    -0.46
     algún
    -0.46
     sesuatu
    -0.46
    SourceChecksum
    -0.45
    stuff
    -0.45
    POSITIVE LOGITS
     hundred
    1.63
     dozen
    1.48
     thousand
    1.37
    hundred
    1.26
     weeks
    1.19
    dozen
    1.15
    thousand
    1.09
     months
    1.05
     hundert
    1.02
     minutes
    0.95
    Activations Density 0.091%

    No Known Activations