© 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. 20-GEMMASCOPE-RES-16K
    11. 2502
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation

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

    LaTeX environments and math formulas

    np_acts-logits-general · gemini-2.0-flash

    aligned, align, split, array

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كمان
    -0.70
    nezeu
    -0.59
    arım
    -0.52
    Bett
    -0.51
    المناصب
    -0.49
     Dominus
    -0.48
    Véxase
    -0.48
     Portuguesa
    -0.47
     entière
    -0.46
     judiciales
    -0.46
    POSITIVE LOGITS
    enumi
    0.70
    jspx
    0.67
    enterOuterAlt
    0.64
    SpringBootTest
    0.59
    enumii
    0.57
    تقاوى
    0.55
    AutoScaleMode
    0.54
     مشين
    0.54
     cref
    0.53
    WebControls
    0.51
    Activations Density 0.098%

    No Known Activations