© 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. 18-GEMMASCOPE-RES-16K
    11. 13254
    Prev
    Next
    INDEX
    Explanations

    elements related to computer programming and data manipulation

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

    Code, file paths, and programming syntax

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.63
     Brand
    -0.46
     Er
    -0.45
     W
    -0.44
     Mont
    -0.43
    /
    -0.43
     ·
    -0.43
     
    -0.42
    strona
    -0.42
     White
    -0.42
    POSITIVE LOGITS
     незавершена
    1.02
    setVerticalGroup
    1.00
    Diweddarwch
    0.97
    AddTagHelper
    0.95
    +#+#
    0.95
    ConstraintMaker
    0.94
    featureID
    0.93
    RenderAtEndOf
    0.92
     otomatig
    0.91
     esternos
    0.90
    Activations Density 0.248%

    No Known Activations