© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14293
    Prev
    Next
    INDEX
    Explanations

    references to unconventional or humorous situations

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

    informal, conversational, or sarcastic commentary in blog posts and casual online writing.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    informal, conversational, highly expressive commentary with interjections, sarcasm, exclamations, and direct address.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     correspondiente
    -0.32
    ceğine
    -0.29
     primarily
    -0.29
     žem
    -0.28
     gydy
    -0.28
     secundario
    -0.28
     Técnico
    -0.28
     personal
    -0.27
    Wirk
    -0.27
    个人
    -0.26
    POSITIVE LOGITS
    GEBURTSDATUM
    0.73
     kaarangay
    0.65
    IntOverflow
    0.64
    TagMode
    0.59
     intptr
    0.59
     utafitiHapana
    0.59
    bleach
    0.59
     bleach
    0.59
     holog
    0.59
    ⏔
    0.58
    Activations Density 0.971%

    No Known Activations