© 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. 3465
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses and brackets

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

    code syntax with nil

    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
    -1.93
     myſelf
    -1.70
     Anſ
    -1.63
     doubtnut
    -1.58
     Reſ
    -1.57
     ་་
    -1.55
     Monfieur
    -1.54
     Diſ
    -1.54
     pleaſure
    -1.53
     uſed
    -1.53
    POSITIVE LOGITS
     
    1.18
     I
    1.14
     y
    1.06
     s
    1.06
     i
    1.06
     A
    1.06
     m
    1.02
     E
    1.01
     a
    1.00
     n
    1.00
    Activations Density 0.027%

    No Known Activations