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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7467
    Prev
    Next
    INDEX
    Explanations

    specific terms and contexts related to scientific and academic concepts

    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
    XmlIgnore
    -0.69
    AddTagHelper
    -0.47
    greenrobot
    -0.45
     AppComponent
    -0.44
     defaultstate
    -0.43
    webElementXpaths
    -0.42
     Waray
    -0.42
     Hentet
    -0.42
     terciopelo
    -0.42
    SystemColors
    -0.41
    POSITIVE LOGITS
    verwijspagina
    0.53
    principalTable
    0.46
     newOwner
    0.45
     otomatig
    0.45
    帖最后由
    0.43
    failures
    0.41
     contextLoads
    0.40
     Administrativna
    0.39
    StoreMessageInfo
    0.39
    ът
    0.37
    Activations Density 0.333%

    No Known Activations