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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 21632
    Prev
    Next
    INDEX
    Explanations

    terms related to parent-child relationships in hierarchical data structures

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

    hierarchical array and tree structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.44
    Derbyniad
    -0.44
    Personendaten
    -0.40
    Transkript
    -0.37
     resourceCulture
    -0.33
     Legis
    -0.31
    الحياه
    -0.31
    HtmlAttribute
    -0.31
     насељу
    -0.30
     ویکی‌پدی
    -0.30
    POSITIVE LOGITS
     hierarchy
    1.70
     hierarchical
    1.67
     hierarchies
    1.48
     Hierarchy
    1.42
     hierarch
    1.42
    hierarchy
    1.40
    Hierarchy
    1.34
    Hierarchical
    1.31
    hier
    1.30
     Hierarchical
    1.30
    Activations Density 0.492%

    No Known Activations