© 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. 9051
    Prev
    Next
    INDEX
    Explanations

    key phrases related to governance and financial transactions

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    actions and conditions

    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
    Sometimes
    -0.63
     Sometimes
    -0.58
     Often
    -0.56
    Espèce
    -0.55
     переписи
    -0.55
    uxxxx
    -0.55
     תמיד
    -0.54
    Often
    -0.54
     sometimes
    -0.53
     alltid
    -0.53
    POSITIVE LOGITS
     reportedly
    1.07
     allegedly
    0.95
     indefinitely
    0.84
     withdrew
    0.81
     announced
    0.81
     unspecified
    0.80
     deadline
    0.79
     temporarily
    0.79
     revoked
    0.77
     unilaterally
    0.77
    Activations Density 0.532%

    No Known Activations