© 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. 11-GEMMASCOPE-RES-16K
    11. 1582
    Prev
    Next
    INDEX
    Explanations

    comparisons highlighting differences or advantages over competitors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    равда
    -0.46
    stateProvider
    -0.44
     şun
    -0.41
     previa
    -0.40
    MemoryWarning
    -0.40
     verba
    -0.39
     Процитовано
    -0.38
    istad
    -0.36
     ExecuteAsync
    -0.36
     sério
    -0.36
    POSITIVE LOGITS
     mergeFrom
    0.67
     otomatig
    0.63
    Personendaten
    0.63
     Wikimedijinoj
    0.63
    EDEFAULT
    0.62
    KommentareTeilen
    0.60
     pulumi
    0.60
     kasarigan
    0.60
     propOrder
    0.60
    ✭✭
    0.60
    Activations Density 0.340%

    No Known Activations