© 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. 16-GEMMASCOPE-RES-16K
    11. 8786
    Prev
    Next
    INDEX
    Explanations

    technical terms related to the assembly and materials used in engineering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Steps in a manufacturing or crafting process

    np_acts-logits-general · gemini-2.0-flash

    cutting shape and form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.88
     '\\;'
    -0.85
     kasarigan
    -0.83
    Personendaten
    -0.79
     themſelves
    -0.74
    NonQuery
    -0.74
    UnknownFields
    -0.74
    InputBorder
    -0.73
     modernisation
    -0.72
     CreateTagHelper
    -0.71
    POSITIVE LOGITS
     final
    0.63
     finished
    0.55
     plan
    0.53
    final
    0.50
     size
    0.48
    Final
    0.46
     draft
    0.45
     model
    0.44
    plan
    0.44
     boss
    0.43
    Activations Density 0.400%

    No Known Activations