© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8874
    Prev
    Next
    INDEX
    Explanations

    terms related to social justice issues and personal accountability

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

    comparison or similarity

    np_acts-logits-general · gemini-2.0-flash

    how things are done

    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
     Meksiku
    -0.59
    dius
    -0.49
    <bos>
    -0.47
    ⓧ
    -0.47
    cellent
    -0.47
    mbrie
    -0.45
    ঘ
    -0.44
    endio
    -0.43
     cele
    -0.43
     öz
    -0.41
    POSITIVE LOGITS
     differently
    1.43
     así
    1.21
     näin
    1.12
     like
    1.11
     demikian
    1.03
     assim
    1.00
     így
    0.99
     slik
    0.96
    このように
    0.94
     böyle
    0.94
    Activations Density 0.500%

    No Known Activations