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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 15316
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and evaluations

    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
    findpost
    -0.98
    WebVitals
    -0.97
    ValueStyle
    -0.97
     AssemblyCulture
    -0.95
    migrationBuilder
    -0.95
    RenderAtEndOf
    -0.91
     Мексичка
    -0.90
     itſelf
    -0.87
     pleaſure
    -0.85
    AddTagHelper
    -0.85
    POSITIVE LOGITS
     who
    0.65
     person
    0.51
     in
    0.51
     senior
    0.49
     non
    0.49
     qualified
    0.48
     
    0.48
    who
    0.47
     persone
    0.46
     har
    0.44
    Activations Density 0.729%

    No Known Activations