© 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. 20-GEMMASCOPE-RES-16K
    11. 8849
    Prev
    Next
    INDEX
    Explanations

    references to the structure and functionality of programming constructs in code

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

    After specific words

    np_acts-logits-general · gemini-2.0-flash

    identifiers and values

    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
    ‍♀️
    -0.55
     boleto
    -0.48
    ‍♂️
    -0.48
    不已
    -0.43
    แหล
    -0.42
    Achtung
    -0.41
    ầy
    -0.41
     लेकर
    -0.40
     unrecogn
    -0.40
    によっては
    -0.39
    POSITIVE LOGITS
     ویکی‌پدی
    1.24
    Personensuche
    1.18
    hoeddwyd
    1.17
    tagHelperRunner
    1.14
     Roskov
    1.13
    RegressionTest
    1.12
     autorytatywna
    1.11
    OGND
    1.11
    AccessorTable
    1.07
    évaluateur
    1.07
    Activations Density 0.382%

    No Known Activations