© 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. 110
    Prev
    Next
    INDEX
    Explanations

    references to MP3 files and formats

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

    MP followed by a number

    np_acts-logits-general · gemini-2.0-flash

    MP followed by media or team names

    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
     wonder
    -1.63
    wonder
    -1.32
     Wonder
    -1.10
     WONDER
    -1.01
    Wonder
    -0.98
     wonders
    -0.96
     wondered
    -0.95
     wondering
    -0.84
     Wunder
    -0.78
    AxisAlignment
    -0.70
    POSITIVE LOGITS
    mybatisplus
    0.76
    mps
    0.70
     MP
    0.67
    MP
    0.67
     Tramp
    0.67
     Efq
    0.65
     étoient
    0.65
     itſelf
    0.63
     MPs
    0.63
     habet
    0.62
    Activations Density 0.188%

    No Known Activations