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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4293
    Prev
    Next
    INDEX
    Explanations

    statements and questions that express opinions or arguments

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

    a condition or implication

    np_acts-logits-general · gemini-2.0-flash

    conditional conjunctions and punctuation

    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
    OGND
    -0.70
     насељу
    -0.70
    DoubleQuotes
    -0.60
    我也是
    -0.59
     saites
    -0.58
     위한
    -0.57
    ()][
    -0.56
     ब्रेकडाउन
    -0.55
     betweenstory
    -0.55
     للمعارف
    -0.53
    POSITIVE LOGITS
     if
    1.34
     If
    1.14
     when
    1.09
    If
    1.04
     hvis
    0.98
     если
    0.95
    如果
    0.94
    if
    0.94
     whenever
    0.93
     kapag
    0.92
    Activations Density 0.937%

    No Known Activations