© 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. 7064
    Prev
    Next
    INDEX
    Explanations

    phrases related to popular cinematic and television characters, especially focusing on awards and critiques

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

    "Doctor"

    np_acts-logits-general · gemini-2.0-flash

    Doctor or House mentions since

    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
    oredCriteria
    -0.75
     pageContext
    -0.71
    fjspx
    -0.65
    ANDUM
    -0.63
     MBS
    -0.61
    TargetException
    -0.60
     MPA
    -0.60
    bilt
    -0.59
     chrétien
    -0.58
    ImageContext
    -0.58
    POSITIVE LOGITS
    Doctor
    0.90
     Doctor
    0.89
     DOCTOR
    0.71
     Dale
    0.64
    doctor
    0.63
    companion
    0.63
    DOCTOR
    0.62
    Dale
    0.60
     doctor
    0.60
    wdriver
    0.58
    Activations Density 0.138%

    No Known Activations