© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10341
    Prev
    Next
    INDEX
    Explanations

    instances of code-related discussions, particularly focusing on errors and debugging in programming contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Followed by a verb ending in -ing

    np_acts-logits-general · gemini-2.0-flash

    building, creating, extracting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     houſe
    -0.78
     ſind
    -0.76
     ―――――
    -0.74
     ſhall
    -0.73
    WarningLevel
    -0.73
    ELTS
    -0.72
     Jefus
    -0.72
     raiſ
    -0.72
     >=",
    -0.71
     auffi
    -0.71
    POSITIVE LOGITS
     my
    0.79
     myself
    0.74
     meu
    0.68
     I
    0.66
    我自己
    0.64
     supposed
    0.63
     mijn
    0.63
    私には
    0.62
     मुझे
    0.60
    my
    0.59
    Activations Density 1.215%

    No Known Activations