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. 5-GEMMASCOPE-RES-16K
    6. 3879
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions and relationships in mathematical or scientific contexts

    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
    DebuggerNonUser
    -0.74
    BeginInit
    -0.69
     ""],
    -0.68
     Roskov
    -0.67
     يتيمه
    -0.67
     bParam
    -0.63
     Civi
    -0.62
    eeq
    -0.61
    Tikang
    -0.60
    StructEnd
    -0.60
    POSITIVE LOGITS
     scolaires
    0.80
     religieuses
    0.69
     étrangères
    0.67
     supérieures
    0.62
     fréquent
    0.62
     malade
    0.61
    tvguidetime
    0.60
     prisonniers
    0.59
     ביותר
    0.58
     soldati
    0.57
    Activations Density 0.594%

    No Known Activations