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. 15-GEMMASCOPE-RES-16K
    6. 2511
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to contracts and property transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     provoc
    -0.53
     metrics
    -0.48
     interaction
    -0.48
     core
    -0.48
     selec
    -0.48
     contribu
    -0.48
     interactions
    -0.47
     Tym
    -0.47
     Premi
    -0.47
     benchmarking
    -0.46
    POSITIVE LOGITS
    ⓧ
    0.93
     avoient
    0.82
     enfans
    0.82
    AndEndTag
    0.81
     aikaa
    0.81
     feroit
    0.79
     étoient
    0.79
    Rüyada
    0.79
     auroit
    0.78
     définiti
    0.76
    Activations Density 1.301%

    No Known Activations