© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7267
    Prev
    Next
    INDEX
    Explanations

    programming structures or elements

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

    Characters after punctuation or special symbols

    np_acts-logits-general · gemini-2.0-flash

    introduction, goddess, sign

    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
    expandindo
    -1.25
    Datuak
    -1.11
    rungsseite
    -1.08
    SharedDtor
    -1.05
    GEBURTSDATUM
    -1.05
    EndGlobalSection
    -1.03
    parsedMessage
    -1.02
    #+#
    -1.02
    StoryboardSegue
    -1.02
    rrggbb
    -1.02
    POSITIVE LOGITS
     non
    0.53
     super
    0.52
    æus
    0.50
     per
    0.48
     “
    0.48
     
    0.43
     man
    0.43
    …
    0.43
     "
    0.43
     di
    0.43
    Activations Density 1.565%

    No Known Activations