© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 896
    Prev
    Next
    INDEX
    Explanations

    keywords related to data handling and programming concepts.

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

    parts of code written in a specific programming language.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    properties or attributes of data structures in programming code, particularly focusing on accessing or manipulating data within objects, arrays, or other complex data types.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Code snippets referencing data, models, or descriptors

    np_acts-logits-general · gemini-2.0-flash

    data and related parameters

    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
    ACT
    -0.49
    CRI
    -0.45
    索
    -0.43
    oldt
    -0.43
     seme
    -0.42
    wla
    -0.42
     bety
    -0.41
    phil
    -0.41
     run
    -0.41
    antin
    -0.40
    POSITIVE LOGITS
     typelib
    0.95
     &&
    0.95
    &&
    0.87
    Personendaten
    0.85
     الرياضيه
    0.85
     &&
    0.81
    yntaxException
    0.78
     NDEBUG
    0.77
     Efq
    0.76
    windowFixed
    0.75
    Activations Density 0.212%

    No Known Activations