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. 7370
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-service and personal choice

    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
    RenderAtEndOf
    -0.76
    CloseOperation
    -0.72
     AssemblyTitle
    -0.71
    HandlerContext
    -0.66
    Derbyniad
    -0.65
    حوالہ
    -0.65
    ngdoc
    -0.64
    comuna
    -0.64
    tagHelperRunner
    -0.61
    BeginInit
    -0.60
    POSITIVE LOGITS
    OGO
    0.45
    mitteilung
    0.44
    自由に
    0.44
    オケ
    0.43
    godic
    0.43
    IRY
    0.42
     bricola
    0.42
    events
    0.41
     bingo
    0.41
    ようになって
    0.41
    Activations Density 0.249%

    No Known Activations