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. 7-GEMMASCOPE-RES-16K
    6. 11659
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of building and compiling software

    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
    بوابة
    -0.91
    XmlAccessorType
    -0.86
    WebVitals
    -0.77
    djangoproject
    -0.75
    AddHtmlAttribute
    -0.74
    XmlEnum
    -0.73
    +#+#
    -0.73
    tonsoft
    -0.70
     defaultstate
    -0.68
    effetto
    -0.68
    POSITIVE LOGITS
     BUILD
    1.22
     Build
    1.21
    build
    1.19
     build
    1.17
    BUILD
    1.15
    Build
    1.14
     builds
    0.94
    Builds
    0.90
    builds
    0.83
     Builds
    0.81
    Activations Density 0.061%

    No Known Activations