© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7241
    Prev
    Next
    INDEX
    Explanations

    errors and exceptions in code or system processes

    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
    StatusOK
    -0.52
    CompleteListener
    -0.46
     pelas
    -0.44
    ">—
    -0.43
    ])){
    -0.43
     eer
    -0.43
    python
    -0.42
    ){
    -0.42
    =[]
    -0.41
    )){
    -0.40
    POSITIVE LOGITS
    BeginContext
    0.88
    WriteTagHelper
    0.85
    tvguidetime
    0.85
    ंदीखरीदारी
    0.83
    Diweddarwch
    0.82
    IsMutable
    0.82
    Geplaatst
    0.80
     تضيفلها
    0.80
    RenderAtEndOf
    0.78
    hésite
    0.78
    Activations Density 0.956%

    No Known Activations