© 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. 14-GEMMASCOPE-RES-16K
    11. 8500
    Prev
    Next
    INDEX
    Explanations

    expressions of strong recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIP
    -0.39
    extAlignment
    -0.39
     Habit
    -0.38
     mona
    -0.37
    LabelTagHelper
    -0.36
     lon
    -0.35
    Vip
    -0.35
     hub
    -0.35
    Abit
    -0.35
     cil
    -0.35
    POSITIVE LOGITS
    出版年
    0.55
    ⓧ
    0.55
    rungsseite
    0.52
     AssemblyProduct
    0.51
    thâu
    0.50
    igshid
    0.50
     kalian
    0.49
     ujednoznacz
    0.49
    ListItemIcon
    0.48
     
    0.48
    Activations Density 0.165%

    No Known Activations