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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1809
    Prev
    Next
    INDEX
    Explanations

    dates, timestamps, and publication information in textual content

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

    Dates or months

    np_acts-logits-general · gemini-2.0-flash

    months and days of the week

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atalos
    -0.55
    */].
    -0.52
    <bos>
    -0.50
    ofile
    -0.46
    ungsbedingungen
    -0.45
    кономі
    -0.44
     alertDialog
    -0.43
     habet
    -0.43
    orszá
    -0.41
    espn
    -0.41
    POSITIVE LOGITS
    BeginContext
    0.81
     محفوظة
    0.79
     propOrder
    0.73
    oredCriteria
    0.70
    下载附件
    0.69
    Suara
    0.68
    Referencie
    0.66
     Tuesday
    0.66
     January
    0.66
     nahilalakip
    0.66
    Activations Density 0.209%

    No Known Activations