© 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. 1911
    Prev
    Next
    INDEX
    Explanations

    references to companies and organizations

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

    before ", Inc." or similar company suffixes

    np_acts-logits-general · gemini-2.0-flash

    company names and suffixes

    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
    Personendaten
    -0.89
     CreateTagHelper
    -0.84
     propOrder
    -0.81
     >=",
    -0.79
    ReusableCell
    -0.76
    UnusedPrivate
    -0.74
    parsedMessage
    -0.73
    Попис
    -0.72
     Préférences
    -0.71
    webElementXpaths
    -0.69
    POSITIVE LOGITS
     Inc
    2.40
    Inc
    1.79
     inc
    1.60
    inc
    1.49
     LLC
    1.45
     INC
    1.43
     Incorporated
    1.43
     Ltd
    1.36
    INC
    1.27
    Ltd
    1.04
    Activations Density 0.253%

    No Known Activations