© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8865
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to computer cooling systems

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

    Heat and thermal energy

    np_acts-logits-general · gemini-2.0-flash

    heat and thermal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.78
     урна
    -0.66
    WithIOException
    -0.60
     ProtoMessage
    -0.60
     Samson
    -0.57
    complexContent
    -0.57
    omock
    -0.56
     gynhyrchwyd
    -0.56
     Elasticity
    -0.56
    ométrique
    -0.55
    POSITIVE LOGITS
     heat
    1.32
     thermal
    1.23
     Heat
    1.15
    Heat
    1.13
    heat
    1.11
     Thermal
    1.09
     heats
    1.05
    Thermal
    1.04
    thermal
    1.03
     HEAT
    0.97
    Activations Density 0.316%

    No Known Activations