© 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-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8848
    Prev
    Next
    INDEX
    Explanations

    references to scheduling appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.60
    dafx
    -0.53
     campeão
    -0.52
     InputDecoration
    -0.50
    fazione
    -0.48
    Statistiche
    -0.48
    
    -0.48
    PARATUS
    -0.48
     picioare
    -0.47
    γραφία
    -0.46
    POSITIVE LOGITS
     appointments
    1.20
     appointment
    1.20
     Appointments
    1.14
     Appointment
    1.10
    Appointments
    1.06
    appointments
    0.97
    Appointment
    0.96
    appointment
    0.96
     APPOINT
    0.90
     appoint
    0.81
    Activations Density 0.144%

    No Known Activations