© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3315
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and import statements in code

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

    Comes before abbreviations or locations

    np_acts-logits-general · gemini-2.0-flash

    abbreviations and acronyms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    gane
    -0.54
    shafen
    -0.52
     doInBackground
    -0.52
    glEnable
    -0.51
    edom
    -0.51
    prepareStatement
    -0.51
    ceda
    -0.51
     Gad
    -0.50
     gaun
    -0.49
     gratification
    -0.48
    POSITIVE LOGITS
     initComponents
    0.56
    原始内容存档于
    0.52
    James
    0.51
    Спасылкі
    0.50
    Spoljašnje
    0.49
     justiça
    0.49
     James
    0.49
    Jet
    0.48
     JR
    0.46
     judiciaire
    0.46
    Activations Density 0.119%

    No Known Activations