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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 3030
    Prev
    Next
    INDEX
    Explanations

    references to historical narratives about slavery and its ongoing impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.92
    NameInMap
    -0.91
     propOrder
    -0.82
    évaluateur
    -0.81
    PreferredItem
    -0.79
    MigrationBuilder
    -0.79
    تقاوى
    -0.76
    RegistryLite
    -0.75
    يكب
    -0.70
    +#+#
    -0.70
    POSITIVE LOGITS
     still
    2.77
    still
    2.53
     Still
    2.33
    Still
    2.33
     STILL
    2.11
     هنوز
    1.97
     todavía
    1.95
     fortfarande
    1.92
     ancora
    1.90
    今でも
    1.81
    Activations Density 0.433%

    No Known Activations