Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15582
    Prev
    Next
    INDEX
    Explanations

    components related to vehicle design and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iasis
    -0.53
     Initialized
    -0.48
     للمعارف
    -0.47
     system
    -0.45
    SYSTEM
    -0.44
     (
    -0.43
     socks
    -0.43
     FACILITY
    -0.43
     Gu
    -0.43
    yonel
    -0.43
    POSITIVE LOGITS
     autorytatywna
    0.85
     Paglinawan
    0.76
    fortawesome
    0.76
     shape
    0.75
    DeleteBehavior
    0.75
     BorderRadius
    0.71
     NUKAT
    0.71
     useRouter
    0.68
    StructEnd
    0.68
     tajam
    0.67
    Activations Density 0.210%

    No Known Activations