© 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. 24-GEMMASCOPE-RES-16K
    6. 14616
    Prev
    Next
    INDEX
    Explanations

    terms related to biometric identification and authentication methods

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

    RFID, biometrics, and identification

    np_acts-logits-general · gemini-2.0-flash

    biometric identification and RFID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bandcamp
    -0.60
    AndEndTag
    -0.54
     coar
    -0.54
    igslist
    -0.53
    rician
    -0.53
    TableField
    -0.53
     INSTR
    -0.52
     rheumat
    -0.49
     Breslau
    -0.48
     cupid
    -0.48
    POSITIVE LOGITS
     biometric
    1.06
     identification
    1.04
     fingerprint
    1.01
     Identification
    0.98
     RFID
    0.97
     bio
    0.95
     reader
    0.91
     Bio
    0.90
    bio
    0.88
     readers
    0.87
    Activations Density 0.249%

    No Known Activations