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. 25-GEMMASCOPE-RES-16K
    6. 3977
    Prev
    Next
    INDEX
    Explanations

    connections between contrasting ideas or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     not
    -2.06
     não
    -1.73
     nicht
    -1.71
    not
    -1.63
     niet
    -1.63
     tidak
    -1.59
     ikke
    -1.56
     neither
    -1.50
     không
    -1.48
     NOT
    -1.47
    POSITIVE LOGITS
    而是
    0.79
     vielmehr
    0.77
    rungsseite
    0.75
     بلکه
    0.68
     autorytatywna
    0.64
     sondern
    0.63
     downright
    0.58
    pyplot
    0.58
     مرئيه
    0.57
    むしろ
    0.56
    Activations Density 0.894%

    No Known Activations