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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 21877
    Prev
    Next
    INDEX
    Explanations

    queries and function calls related to subscription handling in a programming context

    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
    RegistryLite
    -0.67
     Мексичка
    -0.63
    Personendaten
    -0.62
     Administrativna
    -0.60
    TagMode
    -0.60
    Tikang
    -0.59
     оригіналу
    -0.56
    PostInfinity
    -0.52
    Билгалдахарш
    -0.50
     Савезне
    -0.50
    POSITIVE LOGITS
     spectro
    0.40
     Lando
    0.38
     Trade
    0.38
     Spectrometry
    0.38
    odeficiency
    0.36
     spectrometry
    0.36
    DropTable
    0.34
     spectrophoto
    0.34
     balancer
    0.34
     Communication
    0.34
    Activations Density 0.006%

    No Known Activations