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. 21-GEMMASCOPE-RES-16K
    6. 2028
    Prev
    Next
    INDEX
    Explanations

    references to gatherings or events involving groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bland
    -0.55
     gagne
    -0.54
    /*
    -0.54
    Dual
    -0.52
    expandindo
    -0.51
     forceps
    -0.50
     Legg
    -0.50
     scoring
    -0.49
     Ferdinando
    -0.49
     vivió
    -0.49
    POSITIVE LOGITS
     gathered
    2.38
     gather
    2.31
     gathering
    2.25
     gathers
    2.13
     Gather
    2.01
    Gathering
    1.92
    Gather
    1.92
    gathering
    1.91
     Gathering
    1.91
    gather
    1.89
    Activations Density 0.384%

    No Known Activations