© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 2705
    Prev
    Next
    INDEX
    Explanations

    references to various types of mechanical and technical equipment

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

    "equipment" and similar words

    np_acts-logits-general · gemini-2.0-flash

    equipment and its context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
     mergeFrom
    -0.54
    gemeester
    -0.52
    getColumnIndex
    -0.47
    AxisAlignment
    -0.46
    veras
    -0.45
     đúng
    -0.45
     HttpStatus
    -0.44
    PreAuthorize
    -0.44
    winston
    -0.44
    maxLines
    -0.44
    POSITIVE LOGITS
     equipments
    1.06
     equipment
    0.95
     Equip
    0.91
     EQUIPMENT
    0.87
    equipment
    0.85
     Equipment
    0.85
    ContentAlignment
    0.80
    equipped
    0.78
     equipping
    0.77
    Equipment
    0.76
    Activations Density 0.116%

    No Known Activations