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. 12-GEMMASCOPE-RES-16K
    6. 6785
    Prev
    Next
    INDEX
    Explanations

    details about individuals' educational backgrounds and professional history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
     Blacklist
    -0.50
     hu
    -0.47
    ренко
    -0.47
    tager
    -0.46
    ung
    -0.45
    ACHUSETTS
    -0.44
    kev
    -0.43
     đủ
    -0.43
     "
    -0.42
    detroit
    -0.41
    POSITIVE LOGITS
    setVerticalGroup
    0.83
    MarshalTo
    0.76
    TagHelpers
    0.74
     stället
    0.73
     propOrder
    0.64
     FetchType
    0.64
    AddHtmlAttribute
    0.63
    onViewCreated
    0.62
     Efq
    0.62
     systemctl
    0.62
    Activations Density 0.423%

    No Known Activations