© 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. 33-GEMMASCOPE-RES-16K
    11. 3057
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes or disruptions in status or roles

    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
     throughout
    -0.40
    Throughout
    -0.39
    忽略
    -0.39
     протяжении
    -0.39
     Throughout
    -0.38
    DidLoad
    -0.38
     thêm
    -0.37
    throughout
    -0.37
    additional
    -0.36
     adicional
    -0.36
    POSITIVE LOGITS
     altogether
    1.25
     completely
    1.16
     entirely
    1.09
     permanently
    1.00
     Completely
    0.97
    Completely
    0.96
    completely
    0.93
     kokona
    0.90
     całkow
    0.87
     навсегда
    0.86
    Activations Density 0.894%

    No Known Activations