© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 14546
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "custom" in various contexts related to programming or configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELTS
    -0.96
     financeira
    -0.90
     MessageBoxIcon
    -0.89
    JFK
    -0.89
     KeyEvent
    -0.87
     LoginComponent
    -0.86
     незавершена
    -0.85
    ResumeLayout
    -0.85
    WebVitals
    -0.81
     Ril
    -0.80
    POSITIVE LOGITS
     Custom
    1.45
    setCustom
    1.39
    custom
    1.37
     custom
    1.36
    Custom
    1.35
     CUSTOM
    1.27
     customized
    1.19
    CUSTOM
    1.15
     tailored
    1.07
     tailor
    1.04
    Activations Density 0.051%

    No Known Activations