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. 1-GEMMASCOPE-RES-16K
    6. 10112
    Prev
    Next
    INDEX
    Explanations

    terms related to biological research, particularly in the context of cellular and molecular studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.79
    StreetMap
    -0.64
    SharedDtor
    -0.64
    BindingResult
    -0.61
    DebuggerStep
    -0.60
     viewType
    -0.59
     Câmara
    -0.57
     planète
    -0.57
     Laurens
    -0.56
    ühnen
    -0.56
    POSITIVE LOGITS
     cy
    0.93
     CY
    0.84
     Cy
    0.83
    Namara
    0.75
    Cy
    0.72
    CY
    0.72
     cycles
    0.66
     resourceCulture
    0.64
     proto
    0.64
     micros
    0.63
    Activations Density 2.695%

    No Known Activations