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. 22-GEMMASCOPE-RES-16K
    6. 12811
    Prev
    Next
    INDEX
    Explanations

    terms related to heat generation and thermal systems

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

    Generating or producing heat

    np_acts-logits-general · gemini-2.0-flash

    generates heat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIAF
    -0.56
    юй
    -0.46
    cellaneous
    -0.46
     Maynard
    -0.45
     Solidarity
    -0.44
    PKCS
    -0.43
    struts
    -0.42
    VIAF
    -0.42
    mayr
    -0.42
    ystis
    -0.41
    POSITIVE LOGITS
     heat
    2.39
     Heat
    2.08
     hot
    2.06
     heating
    2.05
    Heat
    2.04
     temperature
    2.04
    heat
    2.03
     hotter
    2.02
     heats
    1.98
     heated
    1.86
    Activations Density 0.955%

    No Known Activations