© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7884
    Prev
    Next
    INDEX
    Explanations

    instances of chemical compounds or specific materials and their configurations

    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
     butterknife
    -0.56
    indro
    -0.55
    はじめに
    -0.52
    \}\\
    -0.52
     Head
    -0.51
     Reverso
    -0.49
     правило
    -0.49
     हे
    -0.48
    Head
    -0.48
    iega
    -0.47
    POSITIVE LOGITS
     насељу
    0.77
    InstanceState
    0.68
     ISNI
    0.68
    VIAF
    0.66
     AttributeSet
    0.65
    IntoConstraints
    0.63
    Sucesor
    0.62
    TestingModule
    0.62
    principalTable
    0.61
     PLWABN
    0.57
    Activations Density 0.744%

    No Known Activations