© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3257
    Prev
    Next
    INDEX
    Explanations

    terms related to remote control technology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "remote" and related concepts

    np_acts-logits-general · gemini-2.0-flash

    remote control and location

    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
    Negative Logits
     MessageBoxIcon
    -0.72
    a
    -0.60
     InputDecoration
    -0.56
    vaadin
    -0.54
    domésticos
    -0.54
    GeneratedValue
    -0.53
    expandindo
    -0.52
     grosso
    -0.51
    partimento
    -0.51
     Linien
    -0.50
    POSITIVE LOGITS
    principalTable
    0.86
     remote
    0.86
     REMOTE
    0.84
    remote
    0.82
     Remote
    0.80
    Remote
    0.74
    Datuak
    0.73
     Prox
    0.72
     remot
    0.70
     remotely
    0.68
    Activations Density 0.123%

    No Known Activations