© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6220
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to wrongful death cases and litigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.05
     '\\;'
    -0.96
     snippetHide
    -0.93
     AssemblyVersion
    -0.92
    MigrationBuilder
    -0.90
     pymysql
    -0.89
    SEGUIR
    -0.86
    IContainer
    -0.86
     дописавши
    -0.85
     ComVisible
    -0.84
    POSITIVE LOGITS
    http
    0.70
     http
    0.64
    blog
    0.61
     bloggers
    0.56
     blog
    0.56
    Blog
    0.56
     xrange
    0.56
     blogging
    0.52
    Â
    0.51
    UPDATE
    0.50
    Activations Density 0.738%

    No Known Activations