© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9440
    Prev
    Next
    INDEX
    Explanations

    terms related to alternative medical treatments and community health concepts

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

    "other"

    np_acts-logits-general · gemini-2.0-flash

    other or miscellaneous

    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
    Попис
    -0.77
    ValueStyle
    -0.71
     CreateTagHelper
    -0.63
    andExpect
    -0.61
    ImageContext
    -0.61
    EndContext
    -0.60
    autoconfigure
    -0.60
    IUrlHelper
    -0.59
    WriteTagHelper
    -0.58
    MigrationBuilder
    -0.58
    POSITIVE LOGITS
     miscellaneous
    0.90
    Other
    0.84
    Miscellaneous
    0.83
     Other
    0.82
     misc
    0.82
    Misc
    0.81
     Miscellaneous
    0.80
    CELLANEOUS
    0.80
     Misc
    0.76
    cellaneous
    0.74
    Activations Density 0.269%

    No Known Activations