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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 5523
    Prev
    Next
    INDEX
    Explanations

    terms related to heat and temperature phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orithmic
    -0.98
     вікі
    -0.94
     propOrder
    -0.93
     linkovi
    -0.91
    AccessorTable
    -0.90
     برانيه
    -0.90
    ModelAdmin
    -0.90
    rungsseite
    -0.89
     فريبيس
    -0.88
     Roskov
    -0.88
    POSITIVE LOGITS
     heat
    1.51
     Heat
    1.49
     HEAT
    1.45
    heat
    1.40
    HEAT
    1.38
    Heat
    1.34
     heats
    1.31
     heating
    1.03
    heatmap
    1.02
     Heaton
    0.97
    Activations Density 0.109%

    No Known Activations