© 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. 4-GEMMASCOPE-RES-16K
    11. 10326
    Prev
    Next
    INDEX
    Explanations

    coding phrases and keywords related to account management and verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -1.05
    OGND
    -0.98
    GEBURTSDATUM
    -0.98
    Personendaten
    -0.95
     nahilalakip
    -0.92
    InitVars
    -0.90
     ErrIntOverflow
    -0.87
    CodeAttribute
    -0.87
    AddTagHelper
    -0.84
    featureID
    -0.84
    POSITIVE LOGITS
    ծ
    0.57
     świ
    0.55
     د
    0.54
     kö
    0.53
    ג
    0.53
     przep
    0.52
     ד
    0.52
    ფ
    0.52
     διά
    0.51
     ق
    0.51
    Activations Density 1.819%

    No Known Activations