© 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. 36-GEMMASCOPE-RES-16K
    6. 15703
    Prev
    Next
    INDEX
    Explanations

    references to international collaboration and counter-terrorism efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.63
     fué
    -0.54
    msgTypes
    -0.53
    ConstraintMaker
    -0.53
    majánló
    -0.53
     Bewußt
    -0.52
    vgili
    -0.50
    mögens
    -0.50
    WithIOException
    -0.50
     daß
    -0.49
    POSITIVE LOGITS
     amid
    0.76
     lawmaker
    0.62
    Amid
    0.60
     Amid
    0.59
     lawmakers
    0.57
    ůli
    0.55
     dubbed
    0.55
     atop
    0.55
     eyeing
    0.54
     staffers
    0.54
    Activations Density 0.139%

    No Known Activations