Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 2108
    Prev
    Next
    INDEX
    Explanations

    HTML class attributes in markup syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.86
     @"/
    -0.82
    LookAnd
    -0.77
    (!__
    -0.76
    Personensuche
    -0.73
    IVEREF
    -0.73
    Хьажоргаш
    -0.72
    TProtocol
    -0.72
     postIndex
    -0.70
     Aç
    -0.70
    POSITIVE LOGITS
     class
    0.99
    classnames
    0.95
     Class
    0.88
    classList
    0.77
    Class
    0.76
    className
    0.76
     className
    0.76
    class
    0.75
     CLASS
    0.72
    ClassName
    0.69
    Activations Density 0.040%

    No Known Activations