© 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. 18-GEMMASCOPE-RES-16K
    11. 2889
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and numerical data

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

    Dates followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    date, month, or number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.92
    ItemBackground
    -0.82
     gyhoeddwyd
    -0.79
     kaynağından
    -0.76
     AssemblyCulture
    -0.76
     '\\;'
    -0.75
    rungsseite
    -0.74
     propOrder
    -0.73
     pinulongan
    -0.71
    enterOuterAlt
    -0.71
    POSITIVE LOGITS
    ipt
    0.56
    mặt
    0.53
     Sati
    0.53
     Satt
    0.52
    DateField
    0.51
     yoke
    0.51
    শে
    0.51
    CLOS
    0.50
     Revel
    0.50
    UILabel
    0.49
    Activations Density 0.182%

    No Known Activations