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. 17-GEMMASCOPE-RES-16K
    6. 6852
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to property and trust law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hamp
    -0.58
    ugges
    -0.56
    примеча
    -0.52
     rattle
    -0.49
    Apro
    -0.48
     Souha
    -0.47
     snub
    -0.47
    Portale
    -0.47
    τιά
    -0.46
     Analy
    -0.46
    POSITIVE LOGITS
    mybatisplus
    0.73
     droits
    0.67
    AsUp
    0.63
     rights
    0.63
     légal
    0.62
    ImageContext
    0.61
     recevrez
    0.60
    出版年
    0.60
    OGND
    0.59
     onlyOwner
    0.57
    Activations Density 0.883%

    No Known Activations