© 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. 13-GEMMASCOPE-RES-16K
    11. 10784
    Prev
    Next
    INDEX
    Explanations

    words related to election results and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يكب
    -0.41
    diğim
    -0.39
     jspb
    -0.38
     ProtoMessage
    -0.38
    length
    -0.38
     Greyhound
    -0.38
    active
    -0.36
    tanooga
    -0.36
    secure
    -0.35
    grading
    -0.35
    POSITIVE LOGITS
    IBAction
    0.54
     resultMap
    0.46
    NameInMap
    0.45
    isContained
    0.45
     שוליים
    0.45
     يتيمه
    0.42
    lusconi
    0.42
     setCurrent
    0.41
    ariConfig
    0.41
     NgModule
    0.40
    Activations Density 0.247%

    No Known Activations