© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 12442
    Prev
    Next
    INDEX
    Explanations

    phrases indicating initial actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.57
    ValueStyle
    -0.56
    География
    -0.52
    return
    -0.49
    chluss
    -0.46
     архивлан
    -0.45
    κτηρισ
    -0.43
    著名
    -0.42
     hadapan
    -0.41
    glBindBuffer
    -0.41
    POSITIVE LOGITS
     initially
    1.48
     Initially
    1.32
    Initially
    1.23
     initial
    1.17
     inicialmente
    1.14
    unächst
    1.11
     originally
    1.08
     zunächst
    1.07
     Initial
    1.01
    Initial
    0.97
    Activations Density 0.310%

    No Known Activations