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. 2-GEMMASCOPE-RES-16K
    6. 6675
    Prev
    Next
    INDEX
    Explanations

    terms related to aerospace and engineering contexts

    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
    ^(@)
    -0.83
    Děkuji
    -0.82
    mặt
    -0.80
     autorytatywna
    -0.77
    🏻‍♀️
    -0.72
     dõi
    -0.72
    DockStyle
    -0.71
     Administrativna
    -0.70
     calendriers
    -0.69
     通販
    -0.68
    POSITIVE LOGITS
    ©
    0.50
    <eos>
    0.43
    https
    0.41
    原
    0.40
    ya
    0.40
    RequestMapping
    0.40
    iga
    0.40
     optim
    0.39
    .
    0.39
    hdys
    0.37
    Activations Density 2.670%

    No Known Activations