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. 25-GEMMASCOPE-RES-16K
    6. 5672
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to property and real estate management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ByVersion
    -0.56
    partum
    -0.54
    LookAnd
    -0.54
    jspx
    -0.53
     siff
    -0.51
    dibility
    -0.51
    modium
    -0.50
    Personendaten
    -0.50
     województwie
    -0.50
    ParallelGroup
    -0.49
    POSITIVE LOGITS
     owners
    0.75
     owned
    0.72
    owners
    0.70
     values
    0.69
    holdings
    0.68
    owner
    0.67
     owner
    0.65
     holdings
    0.65
     valuation
    0.64
    owning
    0.63
    Activations Density 0.222%

    No Known Activations