© 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. 2020
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, management decisions, or legal proceedings involving deportation or custody

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

    before auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    deportation and detention

    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
    HtmlAttribute
    -0.67
    AutoScaleMode
    -0.65
     undergoes
    -0.63
    makeConstraints
    -0.59
     autorytatywna
    -0.58
    numerusform
    -0.57
     doInBackground
    -0.55
     surla
    -0.53
    Palmarès
    -0.52
    MemoryWarning
    -0.52
    POSITIVE LOGITS
     imprison
    0.73
     incarcer
    0.67
     detain
    0.62
     punish
    0.60
     induct
    0.58
     expuls
    0.58
     euth
    0.57
     oust
    0.54
     deport
    0.54
     kill
    0.54
    Activations Density 0.616%

    No Known Activations