© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 10815
    Prev
    Next
    INDEX
    Explanations

    instances of sequential actions taken one at a time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.42
     ویکی‌پدی
    -0.40
    Somewhere
    -0.39
     препратки
    -0.38
     саны
    -0.38
    ształ
    -0.37
     Somewhere
    -0.35
     verwijzen
    -0.35
    codename
    -0.35
    yfikacja
    -0.34
    POSITIVE LOGITS
    씩
    0.83
     once
    0.70
    ずつ
    0.69
    一次
    0.68
     gangen
    0.63
    once
    0.60
    parsedMessage
    0.59
     åt
    0.59
    一度
    0.58
    ที
    0.58
    Activations Density 0.160%

    No Known Activations