© 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. 2-GEMMASCOPE-RES-16K
    11. 4345
    Prev
    Next
    INDEX
    Explanations

    character names and terms related to a gaming or fantasy environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getLayout
    -0.51
    SPJ
    -0.49
    上げます
    -0.45
     zve
    -0.44
    Jedis
    -0.43
    یدی
    -0.42
    newArrayList
    -0.42
     ktore
    -0.42
    chọn
    -0.42
    usine
    -0.42
    POSITIVE LOGITS
    ########.
    0.94
    ंदीखरीदारी
    0.77
    Obrázky
    0.72
     kasarigan
    0.71
    bow
    0.70
    InstanceState
    0.69
    abestanden
    0.69
     BOW
    0.68
    parsedMessage
    0.68
    Bow
    0.66
    Activations Density 2.764%

    No Known Activations