© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13130
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal permissions and organizational decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     souff
    -0.29
     kişilik
    -0.27
     faltar
    -0.26
    en
    -0.26
     mejores
    -0.25
     Warte
    -0.25
     selection
    -0.24
     поло
    -0.24
    getDescriptor
    -0.24
     m
    -0.24
    POSITIVE LOGITS
     queſta
    0.88
    
    0.84
     ſind
    0.79
    ⤹
    0.77
     ब्रेकडाउन
    0.77
    ſelben
    0.77
     resourceCulture
    0.75
     ſte
    0.75
     ſeinen
    0.74
     erſt
    0.74
    Activations Density 0.540%

    No Known Activations