© 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 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. 15839
    Prev
    Next
    INDEX
    Explanations

    terms related to choice and independence within various contexts

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

    Following "do" plus an adverb/preposition

    np_acts-logits-general · gemini-2.0-flash

    do as one pleases

    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
     morire
    -0.50
     occorre
    -0.46
     uda
    -0.44
    AnchorStyles
    -0.44
    ühungen
    -0.43
     trug
    -0.43
     Ceux
    -0.43
     État
    -0.43
     réus
    -0.43
     sottile
    -0.42
    POSITIVE LOGITS
     whatever
    1.55
     freely
    1.54
     libremente
    1.31
     Whatever
    1.31
    whatever
    1.26
    自由
    1.23
     dowol
    1.22
    自由に
    1.21
     librement
    1.21
    Whatever
    1.21
    Activations Density 0.431%

    No Known Activations