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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3296
    Prev
    Next
    INDEX
    Explanations

    components and directives in programming or web development contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaynağından
    -0.46
    //*/
    -0.40
     Wä
    -0.40
     betweenstory
    -0.39
    repair
    -0.39
     étrangère
    -0.38
    ********/
    -0.37
     médié
    -0.37
     أج
    -0.37
    getSelected
    -0.37
    POSITIVE LOGITS
     AppComponent
    0.72
     propOrder
    0.70
    SourceChecksum
    0.66
     OnInit
    0.57
    cshtml
    0.54
     nakalista
    0.52
    AppComponent
    0.52
    WebElementEntity
    0.51
    featureID
    0.50
    الدراسه
    0.50
    Activations Density 0.010%

    No Known Activations