© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3129
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing activity and consistency in behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.92
     CreateTagHelper
    -0.82
    setVerticalGroup
    -0.76
    ]='\
    -0.71
    )";
    -0.70
    AddTagHelper
    -0.70
    ConstraintMaker
    -0.69
     مشين
    -0.69
    JspWriter
    -0.65
    rungsseite
    -0.64
    POSITIVE LOGITS
     constantly
    0.96
     constant
    0.91
     Const
    0.80
     ständig
    0.80
     constamment
    0.78
     constante
    0.76
     perpetually
    0.74
     perpetual
    0.74
     постоянно
    0.72
     constantemente
    0.71
    Activations Density 0.171%

    No Known Activations