© 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. 4-GEMMASCOPE-RES-16K
    11. 10792
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or appreciation for someone's time and effort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Зноскі
    -0.76
     ExecuteAsync
    -0.65
    KommentareTeilen
    -0.63
    Portail
    -0.63
    AddTagHelper
    -0.62
     onPage
    -0.58
    GEBURTSDATUM
    -0.58
    paksa
    -0.57
    艸
    -0.57
     CanadaChoose
    -0.56
    POSITIVE LOGITS
     effort
    0.85
     bother
    0.72
     care
    0.72
    effort
    0.71
     Aufwand
    0.67
     pains
    0.65
     efforts
    0.60
    わざわざ
    0.60
     bothered
    0.58
     démarche
    0.58
    Activations Density 0.278%

    No Known Activations