© 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. 24-GEMMASCOPE-RES-16K
    11. 14600
    Prev
    Next
    INDEX
    Explanations

    elements related to programming standards and error handling in code comments

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

    Strict mode and disabling/enabling

    np_acts-logits-general · gemini-2.0-flash

    disable, enable, use strict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.82
     Crusoe
    -0.58
    zungs
    -0.51
     îns
    -0.51
    StreetMap
    -0.51
    webElement
    -0.51
     Etr
    -0.50
    SourceChecksum
    -0.48
    出版年
    -0.47
     Ababa
    -0.47
    POSITIVE LOGITS
     שוליים
    0.60
     Unused
    0.60
     unused
    0.57
    unused
    0.56
     noqa
    0.55
     ASI
    0.54
     cycl
    0.54
     sonar
    0.53
    Unused
    0.52
     Cycl
    0.52
    Activations Density 0.256%

    No Known Activations