© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1012
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and function definitions in programming documents

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

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    syntax punctuation

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     transférez
    -0.69
    +#+#
    -0.68
    andExpect
    -0.66
    LookAnd
    -0.61
    fjspx
    -0.61
     &___
    -0.61
    Enllaces
    -0.60
    parsedMessage
    -0.60
    principalTable
    -0.59
     Roskov
    -0.59
    POSITIVE LOGITS
     nozze
    0.58
     ISTAT
    0.53
     sagrado
    0.53
     fevere
    0.53
     trifle
    0.52
    ifrance
    0.52
     BSEB
    0.51
     marinho
    0.49
     betale
    0.48
     tena
    0.47
    Activations Density 0.240%

    No Known Activations