© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15398
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and their significance

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

    Numerical data within specific ranges

    np_acts-logits-general · gemini-2.0-flash

    numbers in scientific notation or with commas

    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
    izr
    -0.58
    talt
    -0.53
    DOCTYPE
    -0.49
    ńst
    -0.49
    nodoc
    -0.47
     huden
    -0.47
    miyor
    -0.47
    nocache
    -0.47
     montant
    -0.46
     createSprite
    -0.46
    POSITIVE LOGITS
     Paglinawan
    0.73
    +#+#
    0.70
     Efq
    0.62
     noqa
    0.60
    yntaxException
    0.60
     invokingState
    0.58
    createCanvas
    0.58
    NegativeButton
    0.56
     JpaRepository
    0.55
    posedge
    0.54
    Activations Density 0.862%

    No Known Activations