© 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. 18-GEMMASCOPE-RES-16K
    11. 15218
    Prev
    Next
    INDEX
    Explanations

    the word "to" and its variations, as well as phrases indicating movement or direction

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

    Comes before "back to"

    np_acts-logits-general · gemini-2.0-flash

    back to basics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avvic
    -0.58
     חיצוניים
    -0.57
    MLLoader
    -0.56
    lapsingToolbar
    -0.53
    ValueStyle
    -0.53
    twimg
    -0.51
     kautta
    -0.49
    liferay
    -0.49
     linkovi
    -0.49
     hivat
    -0.49
    POSITIVE LOGITS
     basics
    0.89
     Basics
    0.73
    didReceive
    0.71
    ülerin
    0.68
    "")
    0.67
    basics
    0.65
    Personensuche
    0.63
    Basics
    0.63
    cillor
    0.61
    onya
    0.60
    Activations Density 0.163%

    No Known Activations