© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10833
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining or keeping something

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

    "keep" followed by pronoun

    np_acts-logits-general · gemini-2.0-flash

    keep it

    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
     kasarigan
    -0.74
     setuptools
    -0.73
    ----</
    -0.72
     EventArgs
    -0.71
    ThroughAttribute
    -0.71
     مشين
    -0.70
    migrationBuilder
    -0.70
    érape
    -0.68
     DataGridView
    -0.65
     Италијани
    -0.64
    POSITIVE LOGITS
     keep
    0.87
     alive
    0.85
    keep
    0.85
     Keep
    0.79
    Keep
    0.78
     kept
    0.75
     stay
    0.71
     intact
    0.71
     afloat
    0.70
     Kept
    0.69
    Activations Density 0.207%

    No Known Activations