© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 12156
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities within a political or social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.54
    CELLANEOUS
    -0.42
    Халык
    -0.41
    (;;)
    -0.40
    นั้น
    -0.40
     solches
    -0.38
    RenderAtEndOf
    -0.38
    ]+$
    -0.37
    ifrance
    -0.36
    stdafx
    -0.36
    POSITIVE LOGITS
     who
    4.03
    who
    2.77
     whom
    2.75
     quien
    2.61
     whose
    2.31
     quienes
    2.22
     którzy
    2.19
    whom
    2.17
     quién
    2.09
    Who
    2.06
    Activations Density 2.058%

    No Known Activations