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. 6135
    Prev
    Next
    INDEX
    Explanations

    references to cold temperatures and chilly conditions

    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
    Portail
    -1.10
     кӀ
    -1.08
    adaptiveStyles
    -1.04
    Бахар
    -1.03
    yntaxException
    -0.96
    ymce
    -0.89
    erdings
    -0.88
    клопе
    -0.86
     Huffman
    -0.85
     فريبيس
    -0.85
    POSITIVE LOGITS
     Cold
    1.41
     cold
    1.26
    Cold
    1.25
     COLD
    1.25
    COLD
    1.22
    cold
    1.08
    冷
    0.93
     colder
    0.87
     coldest
    0.81
     colds
    0.81
    Activations Density 0.035%

    No Known Activations