© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11486
    Prev
    Next
    INDEX
    Explanations

    terms related to hosting events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    classnames
    -0.69
     Jira
    -0.65
     awakeFromNib
    -0.63
     /\.(
    -0.63
    xaml
    -0.60
    endregion
    -0.59
    SdkVersion
    -0.59
     Cowell
    -0.58
     Belleville
    -0.58
     PartialEq
    -0.57
    POSITIVE LOGITS
     hosting
    3.05
     hosted
    2.92
     hosts
    2.79
     Hosting
    2.77
     host
    2.73
     Host
    2.52
    hosting
    2.50
     Hosted
    2.48
     Hosts
    2.47
    Hosting
    2.44
    Activations Density 0.060%

    No Known Activations