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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9711
    Prev
    Next
    INDEX
    Explanations

    business-related terminology and phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useAppContext
    -0.88
     فريبيس
    -0.85
     المعيارى
    -0.71
    WireFormatLite
    -0.68
     betweenstory
    -0.67
    AccessorTable
    -0.67
    PreferredItem
    -0.66
     Lordships
    -0.65
     mukana
    -0.65
     thorns
    -0.64
    POSITIVE LOGITS
     var
    0.44
    ũng
    0.44
    фици
    0.43
     dưỡng
    0.42
    cpus
    0.40
     -
    0.40
     «
    0.40
    INCREMENT
    0.39
     مست
    0.39
     roof
    0.39
    Activations Density 0.091%

    No Known Activations