© 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. 8-GEMMASCOPE-RES-16K
    6. 10980
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     again
    -0.52
     
    -0.51
    urum
    -0.48
     lé
    -0.46
    urz
    -0.46
    ämme
    -0.45
     artificial
    -0.45
     double
    -0.45
     doble
    -0.45
     penga
    -0.45
    POSITIVE LOGITS
    发表于
    0.78
     quoique
    0.73
    SharedCtor
    0.69
     kasarigan
    0.69
    iibo
    0.67
    AddTagHelper
    0.66
    Parcelize
    0.65
    úgó
    0.65
     leçon
    0.64
    LLocation
    0.64
    Activations Density 0.419%

    No Known Activations