© 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. 5502
    Prev
    Next
    INDEX
    Explanations

    comparison or assignment operations in programming contexts

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

    Code, symbols, or special characters

    np_acts-logits-general · gemini-2.0-flash

    special characters and code snippets

    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
    LabelTagHelper
    -0.72
    SequentialGroup
    -0.71
    ніципалі
    -0.57
    aarrggbb
    -0.52
    writeFieldEnd
    -0.44
     متحده
    -0.43
     smtplib
    -0.43
    ագրություններ
    -0.42
    таратура
    -0.42
    Einzelnachweise
    -0.41
    POSITIVE LOGITS
    rungsseite
    0.68
    TagMode
    0.67
    MigrationBuilder
    0.65
    Alike
    0.64
    TestingModule
    0.61
     combien
    0.60
    Accessors
    0.59
     thèse
    0.58
     tausend
    0.57
    ogeneous
    0.57
    Activations Density 0.147%

    No Known Activations