© 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 EvalsExportsinterp-engineNEWAPI 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. 2493
    Prev
    Next
    INDEX
    Explanations

    concepts related to correctness and achievement in various contexts

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

    way or manner

    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
     كومونز
    -0.61
     pris
    -0.46
    ประกอบ
    -0.42
    pch
    -0.41
     contre
    -0.40
     tegen
    -0.39
     lục
    -0.39
     esto
    -0.38
    Elements
    -0.38
    enuta
    -0.38
    POSITIVE LOGITS
     ways
    1.48
     way
    1.25
     Ways
    1.14
     manières
    1.03
     WAYS
    1.02
     maneras
    1.02
     maneiras
    1.01
     manner
    0.99
    Ways
    0.99
     WAY
    0.94
    Activations Density 0.147%

    No Known Activations