© 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. 20-GEMMASCOPE-RES-16K
    11. 12325
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and phrases indicating claims or results

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

    Following "is," "was," or "been"

    np_acts-logits-general · gemini-2.0-flash

    corroborated, supported, reinforced

    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
     المعيارى
    -0.68
    expandindo
    -0.61
     excelencia
    -0.58
     فريبيس
    -0.57
     utafitiHapana
    -0.57
    ửa
    -0.57
    السكان
    -0.55
    qrstuvwxyz
    -0.54
    Demografía
    -0.54
     transfieras
    -0.53
    POSITIVE LOGITS
     followed
    1.13
     complemented
    1.05
     corroborated
    1.01
     accompanied
    1.00
     reflected
    0.98
     echoed
    0.96
     complimented
    0.95
     countered
    0.93
     aided
    0.92
     supported
    0.90
    Activations Density 0.720%

    No Known Activations