© 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. 7-GEMMASCOPE-RES-16K
    11. 3649
    Prev
    Next
    INDEX
    Explanations

    programming state management indicators and data handling within a component

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -1.01
    存于互联网档案馆
    -1.00
     nakalista
    -0.98
     تضيفلها
    -0.96
    ParallelGroup
    -0.96
    fjspx
    -0.95
     تانيه
    -0.94
    SequentialGroup
    -0.92
    matchCondition
    -0.91
     Roskov
    -0.90
    POSITIVE LOGITS
    ItemBackground
    0.40
    ágos
    0.36
     or
    0.36
     get
    0.35
     en
    0.35
    .
    0.32
     while
    0.32
     re
    0.30
    quito
    0.30
    ORAGE
    0.29
    Activations Density 0.031%

    No Known Activations