Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1350
    Prev
    Next
    INDEX
    Explanations

    structured scientific language and terminology related to research and collaboration in the context of health and environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cyfeiriadau
    -0.71
    MessageTagHelper
    -0.53
     contigo
    -0.53
    Šaltiniai
    -0.53
    Становништво
    -0.52
     disponibilités
    -0.52
     realistas
    -0.49
    istoitu
    -0.48
    DetailView
    -0.47
    pite
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.86
    windowFixed
    0.62
    Brainz
    0.60
     existing
    0.54
     AssemblyCompany
    0.53
    AlterField
    0.52
    FontOfSize
    0.51
    EndContext
    0.50
     pending
    0.49
    existing
    0.49
    Activations Density 0.521%

    No Known Activations