© 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. 34-GEMMASCOPE-RES-16K
    11. 5744
    Prev
    Next
    INDEX
    Explanations

    Java import statements and associated commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -1.57
     beſte
    -1.40
     ſont
    -1.38
     ſche
    -1.35
     ſind
    -1.35
     ſua
    -1.34
     ſei
    -1.33
     pleaſure
    -1.28
     laſſen
    -1.27
     Anſ
    -1.25
    POSITIVE LOGITS
    <unused62>
    0.61
    <unused63>
    0.60
    <unused61>
    0.59
     
    0.47
     th
    0.41
     s
    0.41
     l
    0.40
     r
    0.40
    <unused60>
    0.40
     h
    0.40
    Activations Density 1.420%

    No Known Activations