© 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. 20-GEMMASCOPE-RES-16K
    6. 15105
    Prev
    Next
    INDEX
    Explanations

    timestamps and related metadata indicating creation and modification details in data records

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

    preceding a date or update

    np_acts-logits-general · gemini-2.0-flash

    last update and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.57
     ब्रेकडाउन
    -0.56
     contextLoads
    -0.54
     ويكيميديا
    -0.52
     mapStateToProps
    -0.51
     InputDecoration
    -0.50
     marinho
    -0.49
    GraphicsUnit
    -0.48
    IContainer
    -0.48
    IDENTAL
    -0.48
    POSITIVE LOGITS
     date
    1.33
     Date
    1.26
    Date
    1.23
     timestamp
    1.20
    date
    1.16
    timestamp
    1.13
     DATE
    1.11
     DateTime
    1.09
    datetime
    1.06
     dates
    1.06
    Activations Density 0.182%

    No Known Activations