© 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. 3-GEMMASCOPE-RES-16K
    6. 6027
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and estimation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geſ
    -0.71
    TagMode
    -0.68
     linkovi
    -0.66
     Verſ
    -0.65
     Geiſt
    -0.63
     verſch
    -0.63
     deſſen
    -0.60
    parsedMessage
    -0.60
     ſein
    -0.59
     виправивши
    -0.58
    POSITIVE LOGITS
     transferred
    0.47
     thrown
    0.43
     användas
    0.40
     away
    0.39
     taken
    0.38
    移
    0.38
     conveyed
    0.38
    ải
    0.36
     eliminated
    0.35
     TRANSFER
    0.34
    Activations Density 1.453%

    No Known Activations