© 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. 18-GEMMASCOPE-RES-16K
    11. 8179
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to programming logic and structure

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

    Code, equations, and boolean-like expressions

    np_acts-logits-general · gemini-2.0-flash

    break

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.61
     ioutil
    -0.57
     ExecuteAsync
    -0.56
    ۜ
    -0.51
    iente
    -0.50
     minori
    -0.49
     TestBed
    -0.49
     @"/
    -0.48
    ]")]
    -0.48
     Paglinawan
    -0.48
    POSITIVE LOGITS
    break
    1.88
     break
    1.70
     Break
    1.37
     breaks
    1.30
    Break
    1.28
     BREAK
    1.24
     Breaks
    1.17
    BREAK
    1.15
    breaks
    1.15
     breaking
    1.15
    Activations Density 0.056%

    No Known Activations