© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 641
    Prev
    Next
    INDEX
    Explanations

    references to statistical estimation methodologies

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

    highly referenced statistical and econometric models

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

    year citations

    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
     houſe
    -1.04
     myſelf
    -1.03
     preſent
    -1.01
     Jefus
    -0.99
     fubject
    -0.99
     ſtate
    -0.98
     Efq
    -0.98
     purpoſe
    -0.97
     Majefty
    -0.96
    ^(@)
    -0.95
    POSITIVE LOGITS
     par
    0.58
     l
    0.54
     claimed
    0.52
     para
    0.46
     research
    0.44
     Par
    0.44
     As
    0.44
     can
    0.44
     did
    0.43
     
    0.43
    Activations Density 0.024%

    No Known Activations