© 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. 9-GEMMASCOPE-RES-131K
    11. 50230
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to permutations and their structures in symmetric groups

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

    permutations and rearrangements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bebasan
    -0.39
    ret
    -0.38
    zionalità
    -0.37
    nosa
    -0.37
     rigue
    -0.37
     onBackPressed
    -0.36
    RET
    -0.36
    tilor
    -0.35
    mulos
    -0.35
     Kamal
    -0.35
    POSITIVE LOGITS
     rearrangement
    0.66
     rearrange
    0.66
     rearranged
    0.62
     rearranging
    0.62
     shuffled
    0.62
     shuffling
    0.60
     sorting
    0.58
    shuffle
    0.58
     shuffle
    0.57
     scrambled
    0.57
    Activations Density 0.265%

    No Known Activations