© 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. 24-GEMMASCOPE-RES-16K
    11. 4942
    Prev
    Next
    INDEX
    Explanations

    items and their conditions or states related to clothing and household materials

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

    Past participles and past tense verbs

    np_acts-logits-general · gemini-2.0-flash

    lying, had, been, preserved, laid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.69
    ArrowToggle
    -0.65
    TagHelper
    -0.63
    findpost
    -0.57
    InMillis
    -0.55
     <=",
    -0.53
    EnableWeb
    -0.51
     poda
    -0.50
    mainAxisSize
    -0.50
     AppColors
    -0.50
    POSITIVE LOGITS
     sitting
    1.70
     lying
    1.55
     laying
    1.43
    sitting
    1.38
    Sitting
    1.25
     sit
    1.24
     Sitting
    1.24
     sits
    1.19
     langu
    1.15
     sat
    1.10
    Activations Density 0.286%

    No Known Activations