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. 13327
    Prev
    Next
    INDEX
    Explanations

    scientific processes and methodologies related to experiments involving concentrations and treatments over time

    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
    webElementGuid
    -0.85
     utafitiHapana
    -0.77
     esternos
    -0.70
    XmlAccessType
    -0.69
     disambiguazione
    -0.66
    WithIOException
    -0.66
     فريبيس
    -0.62
    Portály
    -0.61
    XmlIgnore
    -0.59
    icose
    -0.57
    POSITIVE LOGITS
     successively
    0.95
     progressively
    0.89
     stages
    0.87
     levels
    0.82
     successive
    0.77
     sequentially
    0.73
    levels
    0.68
     steps
    0.66
     consecutively
    0.66
     Stages
    0.65
    Activations Density 0.911%

    No Known Activations