© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1395
    Prev
    Next
    INDEX
    Explanations

    conditional phrases involving "if"

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

    conditional statements or hypothetical scenarios

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

    even if

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Either
    -0.84
    either
    -0.81
     Either
    -0.80
     either
    -0.71
     inoltre
    -0.67
    any
    -0.67
     مشين
    -0.66
    จึง
    -0.66
    anything
    -0.65
    Any
    -0.65
    POSITIVE LOGITS
     technically
    0.78
     sometimes
    0.76
     occasionally
    0.72
     theoretically
    0.66
     bazen
    0.65
     they
    0.64
     parfois
    0.64
    Slightly
    0.62
     nominally
    0.61
     unintentionally
    0.61
    Activations Density 0.044%

    No Known Activations