© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 339
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to conditional statements and function declarations

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

    code structure elements related to function definitions and case statements

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

    case, let statement

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     congratulations
    -1.21
     congrats
    -1.11
     Congratulations
    -1.08
     congratulate
    -1.07
    Congratulations
    -1.05
     Congrats
    -1.03
    Congrats
    -0.97
    congratulations
    -0.93
     congrat
    -0.87
     congratulated
    -0.85
    POSITIVE LOGITS
     _
    1.52
     _,
    1.20
    _,
    1.12
    (_
    1.12
     _)
    1.07
     _:
    1.07
    ,_
    1.04
     *_
    1.01
    ._
    0.98
     &_
    0.96
    Activations Density 0.152%

    No Known Activations