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. 3-GEMMASCOPE-RES-16K
    6. 8186
    Prev
    Next
    INDEX
    Explanations

    specialized terms related to biochemical and molecular processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acela
    -0.46
     видел
    -0.46
     toată
    -0.46
    нето
    -0.45
    flü
    -0.45
     quadrinhos
    -0.45
     namelijk
    -0.43
     león
    -0.43
    fillStyle
    -0.43
    cstring
    -0.42
    POSITIVE LOGITS
    kháu
    0.88
    endphp
    0.85
    WithIOException
    0.84
    RegressionTest
    0.83
     يتيمه
    0.82
    ($__
    0.79
     utafitiHapana
    0.79
    windowFixed
    0.77
     disponibilités
    0.77
    fjspx
    0.76
    Activations Density 1.964%

    No Known Activations