© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14767
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and their operations

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

    dictionary or map method calls with dot notation (like `.get()`, `.put()`, `.containsKey()`).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ruote
    -0.39
    setVerticalGroup
    -0.34
     sebou
    -0.34
    Autoritní
    -0.34
    accus
    -0.33
     protoimpl
    -0.33
     pig
    -0.33
     תע
    -0.32
    fillType
    -0.32
    कड
    -0.32
    POSITIVE LOGITS
     entries
    0.75
     entry
    0.69
     Entries
    0.68
    Entry
    0.66
     keys
    0.66
     Entry
    0.65
     ENTRY
    0.60
     objectForKey
    0.60
    FieldDescriptor
    0.58
    entry
    0.57
    Activations Density 0.230%

    No Known Activations