© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14192
    Prev
    Next
    INDEX
    Explanations

    content related to massage therapy and professional qualifications

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

    "massage" or body treatment

    np_acts-logits-general · gemini-2.0-flash

    orthopedic massage

    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
     stabilité
    -0.50
     supernova
    -0.47
     Tern
    -0.46
    projectName
    -0.46
    ectin
    -0.45
     Doherty
    -0.45
     boîtes
    -0.44
     Dichtung
    -0.44
     terce
    -0.44
    estable
    -0.43
    POSITIVE LOGITS
     massage
    1.51
     Massage
    1.30
     massages
    1.28
    Massage
    1.18
    massage
    1.14
     treatments
    0.99
     masaje
    0.93
     treatment
    0.93
     Treatments
    0.91
     masaj
    0.90
    Activations Density 0.099%

    No Known Activations