© 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. 35-GEMMASCOPE-RES-16K
    6. 8322
    Prev
    Next
    INDEX
    Explanations

    HTML and code structure elements such as links and classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.59
    complexContent
    -0.52
    Aholisi
    -0.45
    AndEndTag
    -0.44
     يتيمه
    -0.39
     CreateTagHelper
    -0.38
     aapt
    -0.37
    guien
    -0.36
    andExpect
    -0.34
     ***!
    -0.34
    POSITIVE LOGITS
    expandindo
    0.51
     schließlich
    0.49
     onCreateView
    0.48
     ddelwed
    0.47
     שוליים
    0.47
    Assista
    0.46
    énario
    0.45
    pylab
    0.44
     tslint
    0.44
     finally
    0.44
    Activations Density 0.532%

    No Known Activations