© 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. 22-GEMMASCOPE-RES-16K
    11. 8560
    Prev
    Next
    INDEX
    Explanations

    specific syntax or keywords related to programming or markup languages

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

    File differences or index changes

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal hash strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.96
    Hozzáférés
    -0.75
    awtextra
    -0.75
     resourceCulture
    -0.73
    InstrumentedTest
    -0.72
    __*/
    -0.72
    ContentAsync
    -0.71
    IntoConstraints
    -0.71
    Aiheesta
    -0.70
    Hentet
    -0.70
    POSITIVE LOGITS
    DB
    0.88
    CA
    0.85
    CB
    0.84
    BA
    0.84
    FC
    0.82
    EC
    0.81
    D
    0.80
    DF
    0.79
    E
    0.79
    DA
    0.79
    Activations Density 1.292%

    No Known Activations