© 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. 20-GEMMASCOPE-RES-16K
    11. 4039
    Prev
    Next
    INDEX
    Explanations

    physical items and components in various contexts

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

    Word fragments ending with "a", "o", or "r"

    np_acts-logits-general · gemini-2.0-flash

    cot, bar, pan, cog, fur, pad, eras, toy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onCreateView
    -0.90
    IUrlHelper
    -0.81
    MENTE
    -0.80
    ization
    -0.79
     оригіналу
    -0.79
     nahilalakip
    -0.76
    BibitemShut
    -0.76
     nakalista
    -0.76
    ))))))))
    -0.75
     NgModule
    -0.75
    POSITIVE LOGITS
    々は
    0.51
    々が
    0.51
    zeitige
    0.47
    ot
    0.47
    々
    0.44
    々の
    0.43
    op
    0.43
    ag
    0.43
    raszamy
    0.43
    os
    0.42
    Activations Density 0.643%

    No Known Activations