© 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. 176
    Prev
    Next
    INDEX
    Explanations

    phrases and words that indicate importance or priority in arguments

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

    Adverbs and transition words

    np_acts-logits-general · gemini-2.0-flash

    ordering or emphasis adverbs

    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
    principalColumn
    -0.67
    tonode
    -0.65
     AssemblyCulture
    -0.63
    utilisons
    -0.62
    complexContent
    -0.61
    Diweddarwch
    -0.60
    
    -0.59
    basicConfig
    -0.59
    Бахар
    -0.56
    ällor
    -0.55
    POSITIVE LOGITS
     importantly
    1.24
    tably
    0.80
     Importantly
    0.75
     conversely
    0.73
     interestingly
    0.72
    ureusement
    0.71
     notably
    0.69
    Conversely
    0.69
    ificantly
    0.68
     moreover
    0.63
    Activations Density 0.504%

    No Known Activations