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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68555
    Prev
    Next
    INDEX
    Explanations

    specific numeric values or time-related data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Slot machine

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ftagPool
    -0.50
     AssemblyCulture
    -0.49
     surla
    -0.48
     autorytatywna
    -0.47
    
    -0.46
     inoxidable
    -0.45
    pantalones
    -0.44
     Italijani
    -0.44
     IBOutlet
    -0.43
    balleur
    -0.43
    POSITIVE LOGITS
    BSS
    0.46
    TagMode
    0.43
     CBT
    0.42
    BST
    0.39
    aphone
    0.39
    BDL
    0.39
    期刊论文
    0.39
    NavigationView
    0.38
     PTSD
    0.38
     Jobs
    0.38
    Activations Density 0.001%

    No Known Activations