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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 11144
    Prev
    Next
    INDEX
    Explanations

    references to age or historical significance, particularly emphasizing the concept of being the oldest within a context

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

    oldest son

    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
     Vichy
    -0.39
    cademia
    -0.37
     Guardiola
    -0.37
     Cassini
    -0.36
    सनीय
    -0.36
     HUAWEI
    -0.36
     hoeveel
    -0.36
     Firth
    -0.36
     Sunderland
    -0.36
    しまう
    -0.36
    POSITIVE LOGITS
     oldest
    2.05
    oldest
    1.80
     Oldest
    1.74
     nakalista
    0.94
     äl
    0.91
     earliest
    0.91
     youngest
    0.88
     eldest
    0.85
    Longest
    0.82
     longest
    0.76
    Activations Density 0.003%

    No Known Activations