© 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. 20-GEMMASCOPE-RES-16K
    11. 11684
    Prev
    Next
    INDEX
    Explanations

    hierarchical structures and relationships within systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "the" referring to hierarchical structures

    np_acts-logits-general · gemini-2.0-flash

    ladder, hierarchy, spectrum, pyramid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.58
    rimônio
    -0.52
     AppModule
    -0.44
     AppBundle
    -0.44
     Manchuria
    -0.44
    iastes
    -0.44
     Dionys
    -0.43
     Lucre
    -0.42
     ioutil
    -0.42
    JNIEnv
    -0.41
    POSITIVE LOGITS
     scale
    1.24
     ladder
    1.21
     spectrum
    1.20
     hierarchy
    1.16
     Scale
    1.03
    échelle
    1.02
     escala
    0.98
     SCALE
    0.97
     pyramid
    0.95
    ladder
    0.94
    Activations Density 0.242%

    No Known Activations