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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12352
    Prev
    Next
    INDEX
    Explanations

    terms related to transactional offerings, particularly around free and premium software features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.49
     utafitiHapana
    -0.44
    expandindo
    -0.44
    PreferredItem
    -0.43
    Alloc
    -0.42
     '\\;'
    -0.41
    fromnode
    -0.41
    poj
    -0.41
     Italijanski
    -0.40
    Personendaten
    -0.40
    POSITIVE LOGITS
     subscription
    0.87
     subscriptions
    0.73
     purchase
    0.72
     purchased
    0.70
     premium
    0.65
     paid
    0.63
     Subscription
    0.63
     abonnement
    0.62
     pay
    0.58
    Subscription
    0.58
    Activations Density 0.279%

    No Known Activations