© 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. 11205
    Prev
    Next
    INDEX
    Explanations

    curly braces and their arrangement in mathematical contexts

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

    LaTeX math mode: array environments

    np_acts-logits-general · gemini-2.0-flash

    array and alignment environments

    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
    JspWriter
    -0.88
    DockStyle
    -0.78
    
    -0.74
    ScopeManager
    -0.73
    Datuak
    -0.70
    errHandler
    -0.69
     beginnetje
    -0.68
    AsUp
    -0.68
     Roskov
    -0.68
    WebVitals
    -0.67
    POSITIVE LOGITS
     Lynd
    0.47
    CJK
    0.46
    gdala
    0.42
     Cardinale
    0.42
    {
    0.41
    ^{\
    0.40
    tabular
    0.39
    mtable
    0.39
    array
    0.38
    haled
    0.38
    Activations Density 0.025%

    No Known Activations