© 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. 16-GEMMASCOPE-RES-16K
    11. 14499
    Prev
    Next
    INDEX
    Explanations

    elements related to discrepancies and comparisons within texts

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

    Agreement and matching between items

    np_acts-logits-general · gemini-2.0-flash

    match or mismatch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asteroide
    -0.59
    expandindo
    -0.54
    لينكات
    -0.51
    UnsafeEnabled
    -0.51
    RTLD
    -0.50
    AndEndTag
    -0.50
    RTEE
    -0.49
     Antrieb
    -0.47
    toHaveBeenCalled
    -0.47
     ordinaires
    -0.46
    POSITIVE LOGITS
     mismatch
    1.33
     discrepancy
    1.29
     match
    1.13
     discrepancies
    1.12
     matching
    1.09
     matched
    1.09
     matches
    0.98
     MATCH
    0.96
     Matching
    0.95
    matching
    0.94
    Activations Density 0.759%

    No Known Activations