© 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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 11059
    Prev
    Next
    INDEX
    Explanations

    references to specific programming structures or components in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -1.05
    InjectAttribute
    -0.96
     propOrder
    -0.90
    Personendaten
    -0.87
     disambiguazione
    -0.81
    ThroughAttribute
    -0.75
    SourceChecksum
    -0.73
     <>",
    -0.73
    AndEndTag
    -0.71
    GEBURTSDATUM
    -0.69
    POSITIVE LOGITS
    ẠI
    0.55
    ảnh
    0.55
     Magno
    0.52
     تانيه
    0.51
     Pantheon
    0.51
     optique
    0.51
     plais
    0.49
    τέλε
    0.49
    danno
    0.48
    ificación
    0.48
    Activations Density 0.137%

    No Known Activations