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. 2-GEMMASCOPE-RES-16K
    6. 7071
    Prev
    Next
    INDEX
    Explanations

    technical or medical descriptions related to biological processes and substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    println
    -0.51
     authentic
    -0.49
     authentique
    -0.48
     reunir
    -0.46
    ("]");
    -0.46
    Variation
    -0.45
     naturlig
    -0.44
    setBold
    -0.43
     siyah
    -0.42
     Authentic
    -0.42
    POSITIVE LOGITS
    SequentialGroup
    0.97
    /*
    0.80
    LookAnd
    0.78
    ItemBackground
    0.75
     noDo
    0.74
    AccessorTable
    0.74
    RegistryLite
    0.73
     Приступљено
    0.72
    CrossRef
    0.65
     @"/
    0.65
    Activations Density 3.547%

    No Known Activations