© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 11257
    Prev
    Next
    INDEX
    Explanations

    key points and limitations in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.64
    getSimpleName
    -0.63
    TagMode
    -0.60
     Тогда
    -0.57
    openConnection
    -0.57
     esternos
    -0.55
    enderror
    -0.54
    viewDidLoad
    -0.54
    ollectionView
    -0.52
    Тогда
    -0.52
    POSITIVE LOGITS
     future
    2.03
    future
    1.81
    Future
    1.68
     upcoming
    1.68
     prochain
    1.65
     Future
    1.59
     next
    1.57
    FUTURE
    1.54
     soon
    1.52
     próxima
    1.51
    Activations Density 0.692%

    No Known Activations