© 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. 9837
    Prev
    Next
    INDEX
    Explanations

    conversations and statements related to medical practices and qualifications

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

    "Dr"

    np_acts-logits-general · gemini-2.0-flash

    Dr. Lastname

    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
    Not in Any Lists

    No Comments

    Negative Logits
    WithFormat
    -0.52
    \{\\
    -0.48
    stalt
    -0.47
    וויק
    -0.45
    igshid
    -0.42
    veloppe
    -0.42
     client
    -0.42
    ச்ச
    -0.41
    zien
    -0.41
     UITableViewCell
    -0.41
    POSITIVE LOGITS
     Dr
    3.50
    Dr
    3.26
     dr
    2.60
    dr
    2.28
     Doctor
    2.26
     doctor
    2.11
     Drs
    2.07
    Doctor
    1.96
    دکتر
    1.93
    doctor
    1.87
    Activations Density 0.151%

    No Known Activations