© 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. 14910
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to government or official regulations

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

    Leave, credit, or days off work

    np_acts-logits-general · gemini-2.0-flash

    leave, days, absences, credit

    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
    </thead>
    -0.58
    romas
    -0.54
    yarnpkg
    -0.53
    XmlType
    -0.51
     loudest
    -0.49
     vive
    -0.49
    beet
    -0.49
     Initialized
    -0.49
     indestru
    -0.47
    Descending
    -0.47
    POSITIVE LOGITS
     days
    0.84
     absences
    0.76
     DAYS
    0.74
     hours
    0.73
    Days
    0.71
     Days
    0.70
    days
    0.70
    DAYS
    0.69
     calendar
    0.68
     días
    0.65
    Activations Density 0.270%

    No Known Activations