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. 21-GEMMASCOPE-RES-16K
    6. 3082
    Prev
    Next
    INDEX
    Explanations

    technical terms related to air conditioning systems, specifically focusing on refrigerant properties and charge states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.54
    mány
    -0.49
    arté
    -0.48
    ledem
    -0.48
     Ply
    -0.47
    FirstResponder
    -0.47
     initComponents
    -0.46
     Sanz
    -0.46
     tirer
    -0.45
    Ply
    -0.45
    POSITIVE LOGITS
    TypedDataSet
    0.76
     protoimpl
    0.76
     للاسماء
    0.76
     circulating
    0.65
    ArrowToggle
    0.64
     HX
    0.63
     super
    0.63
     boiler
    0.60
     condenser
    0.59
     fins
    0.59
    Activations Density 0.259%

    No Known Activations