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. 10-GEMMASCOPE-RES-16K
    6. 12561
    Prev
    Next
    INDEX
    Explanations

    instructions related to cleaning and maintenance tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pushFollow
    -0.64
     متعلقه
    -0.59
     disponibilités
    -0.56
     disambiguazione
    -0.53
     emb
    -0.53
    usercontent
    -0.52
     StringTokenizer
    -0.51
    thmus
    -0.47
     Schell
    -0.47
    SpringRunner
    -0.46
    POSITIVE LOGITS
     cleaning
    1.05
    cleaning
    0.90
     cleans
    0.88
     Cleaning
    0.87
     washing
    0.87
     cleaners
    0.86
     scrubbing
    0.86
    Cleaning
    0.85
     detergents
    0.85
     cleansing
    0.83
    Activations Density 0.132%

    No Known Activations