© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13118
    Prev
    Next
    INDEX
    Explanations

    programming constructs and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fasterxml
    -0.33
    Personendaten
    -0.30
    齢
    -0.28
    Rüyada
    -0.27
    isinstance
    -0.27
     pon
    -0.26
    byId
    -0.25
     sarili
    -0.25
     tæ
    -0.25
     suelen
    -0.25
    POSITIVE LOGITS
    UserScript
    0.88
    IUrlHelper
    0.78
    expandindo
    0.72
    IndentedString
    0.69
    出版年
    0.61
    AlterField
    0.60
    TypedDataSet
    0.59
    queryInterface
    0.57
     Autorizaciones
    0.57
    tvguidetime
    0.57
    Activations Density 0.287%

    No Known Activations