© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 7746
    Prev
    Next
    INDEX
    Explanations

    phrases and claims related to current events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obecnie
    -1.39
     recently
    -1.38
     currently
    -1.30
     later
    -1.27
     now
    -1.27
    recently
    -1.25
     teraz
    -1.25
     eventually
    -1.23
     actualmente
    -1.23
     nowadays
    -1.23
    POSITIVE LOGITS
    LookAnd
    0.59
    IUrlHelper
    0.58
    FailureListener
    0.50
     pleaſure
    0.50
    titleMargin
    0.47
     CharSequence
    0.47
     faced
    0.47
     Efq
    0.46
     Houſe
    0.46
    RuleContext
    0.46
    Activations Density 0.749%

    No Known Activations