© 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. 16-GEMMASCOPE-RES-16K
    6. 5751
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time or context for events

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

    Followed by certain prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    in a / in an / in July

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.60
    mogelijk
    -0.58
    Geplaatst
    -0.57
    ότη
    -0.56
    CPtr
    -0.54
    RegistryLite
    -0.53
     trúc
    -0.53
    pakking
    -0.53
    MergeFrom
    -0.53
    innerWidth
    -0.52
    POSITIVE LOGITS
    SequentialGroup
    0.73
     another
    0.51
    middels
    0.50
    UserScript
    0.48
    *{-
    0.47
    ibatis
    0.47
    ')]
    0.45
    ConstraintMaker
    0.45
    ῦ
    0.45
    wiek
    0.45
    Activations Density 0.297%

    No Known Activations