© 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
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11718
    Prev
    Next
    INDEX
    Explanations

    patterns related to frequency and recurrence in events

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

    time expressions related to frequency and duration, such as "every night", "three years running", or "consecutive weeks".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     húmedo
    -0.38
     heuti
    -0.37
    FromJson
    -0.35
    poco
    -0.34
     aydın
    -0.33
     Soon
    -0.33
     étan
    -0.32
     आज
    -0.32
    Few
    -0.32
     aven
    -0.31
    POSITIVE LOGITS
    毎回
    0.67
    每次
    0.66
     everytime
    0.60
    毎年
    0.57
    每一次
    0.56
    tonsoft
    0.55
    endphp
    0.54
     Meksiku
    0.54
     ALWAYS
    0.54
    每年
    0.53
    Activations Density 0.528%

    No Known Activations