© 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. 20-GEMMASCOPE-RES-16K
    6. 11413
    Prev
    Next
    INDEX
    Explanations

    information related to air conditioning and temperature control

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

    air or ventilation

    np_acts-logits-general · gemini-2.0-flash

    air movement and quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.69
     utafitiHapana
    -0.65
     autorytatywna
    -0.53
    تقاوى
    -0.52
    Réalisation
    -0.52
    processable
    -0.52
    礁
    -0.52
    دانشنامهٔ
    -0.50
    TargetException
    -0.49
    webElementXpaths
    -0.49
    POSITIVE LOGITS
     air
    1.83
     ventilation
    1.63
     airflow
    1.50
    air
    1.47
    Air
    1.41
     Air
    1.39
     venti
    1.32
     Ventilation
    1.31
     AIR
    1.30
    AIR
    1.26
    Activations Density 0.238%

    No Known Activations