© 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. 23-GEMMASCOPE-RES-16K
    11. 10205
    Prev
    Next
    INDEX
    Explanations

    terms related to visibility and stealth, particularly in the context of technology or devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OneToMany
    -0.43
    exitRule
    -0.41
    PerformLayout
    -0.40
    SequentialGroup
    -0.39
     SafeMath
    -0.37
    annica
    -0.35
    reportWebVitals
    -0.35
    oneofs
    -0.34
     Foire
    -0.34
    AddTagHelper
    -0.34
    POSITIVE LOGITS
     inconspicuous
    0.93
     concealment
    0.89
     concealed
    0.86
     disguised
    0.85
     concealing
    0.82
     conceal
    0.80
     disguise
    0.79
     hiding
    0.79
     ocultar
    0.79
     indistingu
    0.78
    Activations Density 0.459%

    No Known Activations