© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    references to licensing and code file structures

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

    is simulating

    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
     still
    -3.02
    still
    -2.82
    Still
    -2.64
     Still
    -2.59
     STILL
    -2.30
     continue
    -2.28
     continues
    -2.24
    continue
    -2.22
     fortfarande
    -2.20
     weiterhin
    -2.19
    POSITIVE LOGITS
     كومونز
    0.72
    insee
    0.54
    OGND
    0.51
    umas
    0.48
    RegistryLite
    0.48
    ]^{-
    0.45
    TRIBUTES
    0.44
    ingue
    0.44
     esf
    0.44
    licants
    0.43
    Activations Density 0.414%

    No Known Activations