© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 1461
    Prev
    Next
    INDEX
    Explanations

    phrases related to therapy services and scheduling appointments

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

    free sessions or hourly bookings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dévelo
    -0.34
     gegangen
    -0.31
    elcome
    -0.31
     externally
    -0.31
    mitting
    -0.31
     lettore
    -0.31
     jurado
    -0.29
     sinyal
    -0.28
     zewnętr
    -0.28
    ßerdem
    -0.28
    POSITIVE LOGITS
     session
    0.88
     consultations
    0.85
     sessions
    0.83
     hour
    0.81
     hourly
    0.76
     consultation
    0.75
     AssemblyCulture
    0.75
     HOUR
    0.74
     booking
    0.74
     Session
    0.73
    Activations Density 0.029%

    No Known Activations