© 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. 33-GEMMASCOPE-RES-16K
    6. 8253
    Prev
    Next
    INDEX
    Explanations

    tips and recommendations related to air conditioning and maintaining indoor climate control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.44
    قایناقلار
    -0.42
    ardino
    -0.40
    Rename
    -0.38
    PushMatrix
    -0.38
    homonymie
    -0.37
     Vial
    -0.37
     Rame
    -0.37
    BeginContext
    -0.36
     cioccolato
    -0.36
    POSITIVE LOGITS
     ventilation
    1.55
     Ventilation
    1.34
     venti
    1.31
    Ventilation
    1.27
     ventilación
    1.25
     airflow
    1.23
    ventilation
    1.20
     ventilated
    1.14
     air
    1.11
     vents
    1.11
    Activations Density 0.325%

    No Known Activations