© 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. 5965
    Prev
    Next
    INDEX
    Explanations

    discussions related to self-reflection or personal feelings

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

    Japanese punctuation 。

    np_acts-logits-general · gemini-2.0-flash

    。ねえ

    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
    bootstrapcdn
    -0.71
    AnchorStyles
    -0.68
    XmlAccessType
    -0.65
    consulté
    -0.62
     dég
    -0.61
     nessuno
    -0.58
    grà
    -0.57
     kiin
    -0.56
     Anſ
    -0.55
     accett
    -0.54
    POSITIVE LOGITS
     latter
    0.58
    しかし
    0.57
    ையில்
    0.57
    しかも
    0.57
    ificantly
    0.56
    ただし
    0.55
    그리고
    0.55
     זאת
    0.54
    }{*}{}
    0.54
    そのため
    0.54
    Activations Density 0.101%

    No Known Activations