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. 6083
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation, particularly those involving powers and norms

    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
    ál
    -0.73
     Laird
    -0.62
    le
    -0.62
     Diana
    -0.58
    ala
    -0.58
    lek
    -0.58
    ity
    -0.57
    B
    -0.57
     Vela
    -0.55
    ora
    -0.54
    POSITIVE LOGITS
    )^{
    2.46
    })^{
    1.77
    )^{\
    1.68
    )^
    1.62
    |^{
    1.56
    ]^{
    1.45
    )^(
    1.39
    )_{
    1.35
    })^
    1.32
    )|^{
    1.32
    Activations Density 0.173%

    No Known Activations