© 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. 18-GEMMASCOPE-RES-16K
    11. 3004
    Prev
    Next
    INDEX
    Explanations

    programming structures and syntax used in code

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

    Code-related tokens after opening brackets

    np_acts-logits-general · gemini-2.0-flash

    conditional execution and returns

    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
     Roskov
    -0.94
     ostavi
    -0.92
    Vidite
    -0.90
    ंदीखरीदारी
    -0.88
    openzeppelin
    -0.87
    SuppressMessage
    -0.87
     تضيفلها
    -0.86
    HasAnnotation
    -0.83
    InjectAttribute
    -0.80
    kháu
    -0.79
    POSITIVE LOGITS
    return
    0.54
    Hence
    0.51
     then
    0.50
     return
    0.49
     Hence
    0.47
     Thus
    0.46
    Then
    0.46
    catch
    0.45
     alors
    0.44
    piti
    0.43
    Activations Density 0.251%

    No Known Activations