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. 2052
    Prev
    Next
    INDEX
    Explanations

    structured data elements and their attributes

    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
    rrggbb
    -0.89
    LLocation
    -0.67
    buttonBar
    -0.67
    kháu
    -0.67
    WithIOException
    -0.59
    SuccessListener
    -0.55
    ethene
    -0.55
     Intention
    -0.55
    engertian
    -0.55
     sinned
    -0.54
    POSITIVE LOGITS
     يتيمه
    0.54
     transfieras
    0.49
    }{*}{}
    0.47
     nonatomic
    0.45
    ORUM
    0.44
    VENT
    0.44
     Normdatei
    0.41
     tqdm
    0.41
     disambiguazione
    0.40
    tagHelperRunner
    0.40
    Activations Density 0.091%

    No Known Activations