© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4614
    Prev
    Next
    INDEX
    Explanations

    references to political manipulation and historical interventions, particularly involving the overthrow of leaders and corporate interests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specialise
    -0.48
     étoit
    -0.47
    responsibility
    -0.44
     reasonableness
    -0.44
    λίου
    -0.44
     lyst
    -0.43
    formatics
    -0.42
    Responsibility
    -0.42
     civilisation
    -0.41
     forfait
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    0.79
     profit
    0.72
     lucrative
    0.69
    bootstrapcdn
    0.68
     profitable
    0.66
     profits
    0.64
    WithIOException
    0.62
     Profit
    0.62
     marketable
    0.58
     CanadaChoose
    0.57
    Activations Density 0.431%

    No Known Activations