© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 10138
    Prev
    Next
    INDEX
    Explanations

    structured data related to software development, specifically focusing on code snippets and data structures

    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
    ActivityResult
    -0.58
    Aiheesta
    -0.52
     Sicher
    -0.48
    warm
    -0.47
    DataBean
    -0.45
     Warm
    -0.45
     dirancang
    -0.45
     hű
    -0.44
     hảo
    -0.44
     czarne
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    1.09
    Personendaten
    1.01
    الإنجليزية
    0.73
    RetentionPolicy
    0.72
     CreateTagHelper
    0.71
    >{@
    0.70
    rungsseite
    0.69
    ]")]
    0.69
    Etimología
    0.68
    WriteTagHelper
    0.65
    Activations Density 0.482%

    No Known Activations