© 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. 2929
    Prev
    Next
    INDEX
    Explanations

    references to specific components and concepts related to programming and data structures

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

    parts and components

    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
     Roskov
    -1.04
    verwijspagina
    -0.99
     resourceCulture
    -0.97
     Мексичка
    -0.96
     ModelExpression
    -0.96
    ]--;
    -0.94
    (!__
    -0.93
    SharedCtor
    -0.92
     kasarigan
    -0.90
    клопе
    -0.89
    POSITIVE LOGITS
     part
    3.40
    part
    2.80
     portion
    2.66
     parte
    2.59
    Part
    2.52
     parts
    2.48
     Part
    2.32
    部分
    2.10
     portions
    2.10
     PART
    2.08
    Activations Density 0.975%

    No Known Activations