© 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 EvalsExportsinterp-engineNEWAPI 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. 7256
    Prev
    Next
    INDEX
    Explanations

    phrases conveying numerical or statistical information

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

    Mentions a year

    np_acts-logits-general · gemini-2.0-flash

    months and years

    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
    GEBURTSDATUM
    -0.91
    MigrationBuilder
    -0.89
     تضيفلها
    -0.83
    aarrggbb
    -0.80
    QMetaType
    -0.79
    PreferredItem
    -0.78
    )++;
    -0.77
    CppMethod
    -0.75
    }))
    -0.75
    expandindo
    -0.73
    POSITIVE LOGITS
     year
    0.54
     December
    0.52
     March
    0.51
     November
    0.51
     February
    0.51
     April
    0.49
    سال
    0.49
     June
    0.49
     January
    0.48
    orianCalendar
    0.48
    Activations Density 0.163%

    No Known Activations