© 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. 94
    Prev
    Next
    INDEX
    Explanations

    words related to verification and confirmation processes

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

    keywords and identifiers related to programming or technical specifications

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

    Croatian/Serbian prefixes

    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
     itſelf
    -1.37
     Efq
    -1.34
     myſelf
    -1.27
     Jefus
    -1.26
    ^(@)
    -1.25
    DockStyle
    -1.21
    ſelf
    -1.21
     Majefty
    -1.21
     themſelves
    -1.19
     iſt
    -1.17
    POSITIVE LOGITS
    mon
    0.59
    ver
    0.53
    sp
    0.52
    (
    0.52
    je
    0.51
    tre
    0.51
    get
    0.51
    top
    0.51
    ah
    0.51
    tr
    0.51
    Activations Density 0.045%

    No Known Activations