© 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. 8472
    Prev
    Next
    INDEX
    Explanations

    references to actions or procedures related to cleaning, discarding, and maintaining items or conditions

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

    exclusions or discrepancies

    np_acts-logits-general · gemini-2.0-flash

    identify excluded items

    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
    χεία
    -0.51
    Precise
    -0.49
    мені
    -0.47
     respectivos
    -0.46
    تمع
    -0.46
    tdessen
    -0.46
     invokingState
    -0.46
    multiple
    -0.45
    protoimpl
    -0.45
    hashtags
    -0.44
    POSITIVE LOGITS
     those
    0.91
     items
    0.86
     excluded
    0.81
     exclusions
    0.78
    那些
    0.76
     aquellos
    0.73
    those
    0.73
     những
    0.73
     exclusion
    0.72
     aquellas
    0.71
    Activations Density 1.024%

    No Known Activations