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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 14172
    Prev
    Next
    INDEX
    Explanations

    references to the concept of renewal or expiration, particularly in the context of agreements, leases, or support statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.94
     Eich
    -0.89
    सन्दर्भ
    -0.77
    ControllerTest
    -0.76
    SharedDtor
    -0.76
    awtextra
    -0.74
     Castor
    -0.73
    pidou
    -0.73
    FailureListener
    -0.72
    Sucesor
    -0.71
    POSITIVE LOGITS
    Pros
    1.18
     Pros
    1.09
     Renewal
    1.05
     renewal
    1.01
    renew
    0.97
    pros
    0.97
     pros
    0.96
     renew
    0.95
    Renew
    0.94
     Renew
    0.93
    Activations Density 0.140%

    No Known Activations