© 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. 21-GEMMASCOPE-RES-16K
    11. 14808
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance metrics related to vehicles and machinery

    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
    MessageTagHelper
    -0.68
    Jereo
    -0.62
    writeFieldEnd
    -0.59
    acaktır
    -0.56
     виправивши
    -0.54
    porus
    -0.54
    BeginContext
    -0.50
     pinulongan
    -0.50
    obium
    -0.49
     beginnetje
    -0.49
    POSITIVE LOGITS
     reaching
    1.61
     reach
    1.49
     reaches
    1.47
     Reaching
    1.41
    Reaching
    1.38
    reaching
    1.37
     reached
    1.34
    reach
    1.22
    Reach
    1.21
    reached
    1.21
    Activations Density 0.380%

    No Known Activations