Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11743
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and structures, particularly involving complex functions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.93
     informée
    -0.87
    interopRequire
    -0.79
     noDo
    -0.75
    SourceChecksum
    -0.74
     հղումներ
    -0.73
    rungsseite
    -0.69
    reportWebVitals
    -0.68
    يميديا
    -0.68
     CreateTagHelper
    -0.66
    POSITIVE LOGITS
    ]")]
    0.34
     khởi
    0.33
    ┅
    0.33
     Seil
    0.32
     Eggers
    0.32
    ==============
    0.32
     area
    0.31
    DNEY
    0.31
     fica
    0.31
     City
    0.31
    Activations Density 1.542%

    No Known Activations