Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3967
    Prev
    Next
    INDEX
    Explanations

    dates and references to legal or financial documents

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

    Dates in January or February

    np_acts-logits-general · gemini-2.0-flash

    dates with months

    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
    ias
    -0.54
    PointSize
    -0.49
     nudo
    -0.46
     Abend
    -0.45
    closedir
    -0.43
    night
    -0.42
    assemblée
    -0.42
    BindingSource
    -0.41
    тье
    -0.41
     inserire
    -0.41
    POSITIVE LOGITS
    +#+#
    0.76
    Демографія
    0.73
     autorytatywna
    0.69
     okuyayım
    0.66
     оригіналу
    0.65
    ItemBackground
    0.64
    ArgsConstructor
    0.63
    dataclass
    0.63
     propOrder
    0.63
    CrossRef
    0.62
    Activations Density 0.259%

    No Known Activations