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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 30726
    Prev
    Next
    INDEX
    Explanations

    references to programming and data structure operations

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     aktiviteter
    -0.37
     preghiera
    -0.35
    JvmStatic
    -0.35
    BrowserModule
    -0.35
     CreateTagHelper
    -0.33
     @"/
    -0.33
     aihe
    -0.33
    Rgds
    -0.33
     aplicado
    -0.32
    antMatchers
    -0.32
    POSITIVE LOGITS
     CURIAM
    0.59
    WireFormatLite
    0.50
    قایناق‌لار
    0.47
    "");
    0.47
    Según
    0.47
     happily
    0.47
    MemoryWarning
    0.46
     orch
    0.46
    xase
    0.46
    Newswire
    0.44
    Activations Density 0.068%

    No Known Activations