© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9239
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and qualifiers

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

    Conditional statements and hypothetical situations

    np_acts-logits-general · gemini-2.0-flash

    even if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -0.76
     Either
    -0.74
     natomiast
    -0.71
    either
    -0.67
     either
    -0.61
     inoltre
    -0.60
    また
    -0.59
     επίσης
    -0.58
    まず
    -0.56
    要么
    -0.56
    POSITIVE LOGITS
     sekal
    1.01
     apparente
    0.79
     seemingly
    0.67
     ostensibly
    0.67
     technically
    0.64
     nominally
    0.63
     sometimes
    0.63
     admittedly
    0.62
     казалось
    0.62
     bazen
    0.61
    Activations Density 0.234%

    No Known Activations