© 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. 0-GEMMASCOPE-RES-16K
    11. 14795
    Prev
    Next
    INDEX
    Explanations

    mentions of nickel and related materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     africains
    -0.38
    tgär
    -0.36
     fermés
    -0.36
     dévelo
    -0.35
     TextAppearance
    -0.35
     étend
    -0.34
     enregistrer
    -0.34
    glises
    -0.34
     fufficient
    -0.33
    ンズ
    -0.32
    POSITIVE LOGITS
     ni
    2.48
     Ni
    2.42
    Ni
    2.14
     NI
    2.09
     nickel
    2.00
    ni
    1.97
     nic
    1.95
     nik
    1.90
     ни
    1.88
     nip
    1.88
    Activations Density 1.173%

    No Known Activations