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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4766
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     supposedly
    -0.73
     Parece
    -0.63
     stupidly
    -0.62
    SharedDtor
    -0.61
     Presumably
    -0.61
     goddamn
    -0.60
     weirdly
    -0.60
     sometimes
    -0.58
     presumably
    -0.58
    뀔
    -0.58
    POSITIVE LOGITS
     Utilize
    0.58
    Utiliz
    0.57
     utilize
    0.55
     utilizes
    0.55
     
    0.53
     tallied
    0.52
     Individ
    0.51
    featureID
    0.49
     utilizing
    0.48
     sophomore
    0.48
    Activations Density 0.205%

    No Known Activations