© 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. 9106
    Prev
    Next
    INDEX
    Explanations

    commands or actions indicating the act of doing something

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

    "Do" followed by a general pronoun or determiner

    np_acts-logits-general · gemini-2.0-flash

    doing this or that

    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
     betweenstory
    -1.06
    WebElementEntity
    -0.83
    RegressionTest
    -0.83
     houſe
    -0.80
    AndEndTag
    -0.78
     doubtnut
    -0.77
     TextInputType
    -0.73
    IntoConstraints
    -0.73
    ſelf
    -0.72
    Derbyniad
    -0.71
    POSITIVE LOGITS
     things
    0.94
     something
    0.85
     it
    0.81
     everything
    0.78
     a
    0.76
     the
    0.71
     thing
    0.71
     what
    0.70
     anything
    0.69
     nothing
    0.68
    Activations Density 0.111%

    No Known Activations