Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15336
    Prev
    Next
    INDEX
    Explanations

    terms related to thermodynamic laws and processes

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

    temperature, heat, or thermodynamics

    np_acts-logits-general · gemini-2.0-flash

    temperature

    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
    Хро
    -0.46
    etas
    -0.45
    AUTHENT
    -0.44
     Byr
    -0.42
     timely
    -0.41
     sĩ
    -0.41
    FilterChain
    -0.40
    inline
    -0.40
    žia
    -0.40
     Fino
    -0.40
    POSITIVE LOGITS
    PreferredItem
    0.90
     temperature
    0.89
     Temperature
    0.85
    temperature
    0.82
     temperatures
    0.81
    Temperature
    0.79
     Temperatures
    0.79
     jspb
    0.79
    expandindo
    0.78
    Temper
    0.76
    Activations Density 0.548%

    No Known Activations