© 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. 9072
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to programming and systems development

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

    Follows "to" (often infinitive verbs)

    np_acts-logits-general · gemini-2.0-flash

    accomplish goals

    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
    writeFieldEnd
    -0.65
    ftagPool
    -0.64
    出版年
    -0.58
     consultato
    -0.55
     nakalista
    -0.53
    InjectAttribute
    -0.53
    aarrggbb
    -0.51
    atul
    -0.51
    IsMutable
    -0.51
     correctes
    -0.48
    POSITIVE LOGITS
     accomplish
    1.18
     melakukannya
    1.09
     accomplishing
    1.08
     nisso
    1.03
     hierfür
    1.01
    就是这样
    0.99
     accomp
    0.98
     daarvoor
    0.97
    そのような
    0.93
     doing
    0.92
    Activations Density 0.585%

    No Known Activations