© 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. 449
    Prev
    Next
    INDEX
    Explanations

    numerical data and percentages in contexts related to health statistics

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

    Percentages and ratios

    np_acts-logits-general · gemini-2.0-flash

    percentages and ratios

    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
    RenderAtEndOf
    -0.95
    grà
    -0.71
    WithIOException
    -0.60
     صوتيه
    -0.58
    AnchorTagHelper
    -0.58
    cèse
    -0.55
    ValueGenerated
    -0.54
    зулта
    -0.52
    ValueStyle
    -0.52
     vantaggio
    -0.50
    POSITIVE LOGITS
     createSprite
    0.59
    BagLayout
    0.52
     /**
    0.50
    slidesToShow
    0.49
    Saluti
    0.49
    ngdoc
    0.49
    urlpatterns
    0.49
     createSlice
    0.49
    ollectionView
    0.48
    iteiten
    0.48
    Activations Density 0.239%

    No Known Activations