© 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. 20-GEMMASCOPE-RES-16K
    11. 2506
    Prev
    Next
    INDEX
    Explanations

    quantities related to time or monetary compensation in a service context

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

    Following "up" or "to" and indicating a limit

    np_acts-logits-general · gemini-2.0-flash

    maximum limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.73
    GLFW
    -0.60
    IsRequired
    -0.58
    aarrggbb
    -0.54
    انيف
    -0.52
     transfieras
    -0.52
    kheim
    -0.52
    himu
    -0.52
    Required
    -0.51
    DebuggerNonUser
    -0.50
    POSITIVE LOGITS
     maximum
    1.75
     max
    1.61
     Maximum
    1.60
    maximum
    1.59
    Maximum
    1.54
     máximo
    1.51
    max
    1.51
     MAXIMUM
    1.42
     maksimal
    1.41
     massimo
    1.40
    Activations Density 0.400%

    No Known Activations