© 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. 16-GEMMASCOPE-RES-16K
    11. 13344
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate checking or reviewing content

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

    Imperative verbs followed by "at" or "the"

    np_acts-logits-general · gemini-2.0-flash

    look at or check out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    borderSide
    -0.60
    inquirer
    -0.57
    brainly
    -0.56
     fallu
    -0.54
    uesto
    -0.54
     PLW
    -0.52
    θρω
    -0.52
    írito
    -0.52
     Scy
    -0.51
     XNUMX
    -0.50
    POSITIVE LOGITS
    AndEndTag
    0.69
     saja
    0.59
    ViewFeatures
    0.58
    OGND
    0.57
     atenta
    0.56
     xem
    0.56
     how
    0.55
     autorytatywna
    0.54
    LabelTagHelper
    0.54
     '\\;'
    0.54
    Activations Density 0.130%

    No Known Activations