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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14904
    Prev
    Next
    INDEX
    Explanations

    references to the federal level of government

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

    "the" followed by a time-related word

    np_acts-logits-general · gemini-2.0-flash

    beginning of a phrase

    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
     MonoBehaviour
    -0.65
    StoryboardSegue
    -0.61
     Huguen
    -0.60
     mergeFrom
    -0.59
    SourceChecksum
    -0.55
    ToBounds
    -0.54
    LabelTagHelper
    -0.54
    URLConnection
    -0.54
    swire
    -0.52
    setVerticalGroup
    -0.52
    POSITIVE LOGITS
     end
    1.01
     least
    0.99
     forefront
    0.88
     outset
    0.85
     helm
    0.81
     expense
    0.80
    tempted
    0.80
    expense
    0.80
     discretion
    0.79
    Least
    0.77
    Activations Density 0.067%

    No Known Activations