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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Post
    5. 12-GEMMASCOPE-RES-1M
    6. 11
    Prev
    Next
    INDEX
    Explanations

    terms related to blood disorders and abnormalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Décès
    -0.46
     representation
    -0.46
     @
    -0.45
    rsc
    -0.44
    CHN
    -0.44
    /***/
    -0.44
    мин
    -0.43
     us
    -0.43
     Sab
    -0.42
     sito
    -0.42
    POSITIVE LOGITS
     ligiloj
    0.93
    Демографія
    0.79
    ValueStyle
    0.79
    afficheront
    0.78
     $_"
    0.77
    HasBeenSet
    0.75
    Personendaten
    0.75
    WithIOException
    0.75
    cythe
    0.74
    المناصب
    0.72
    Activations Density 0.011%

    No Known Activations