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. 12-GEMMASCOPE-RES-16K
    6. 4109
    Prev
    Next
    INDEX
    Explanations

    components and keywords related to software development and graphical user interface design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.74
     ddelweddau
    -0.68
    릉
    -0.57
    ValueStyle
    -0.56
    WindowConstants
    -0.55
    Rhestr
    -0.54
     Broome
    -0.54
     Cato
    -0.53
     Estes
    -0.53
     realms
    -0.53
    POSITIVE LOGITS
    Controls
    1.65
    rungsseite
    0.94
     Controls
    0.89
     controls
    0.85
    controls
    0.84
     CONTROLS
    0.80
    lateinit
    0.70
     lateinit
    0.65
    ontrol
    0.61
     незавершена
    0.61
    Activations Density 0.005%

    No Known Activations