© 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. 15-GEMMASCOPE-RES-16K
    6. 13035
    Prev
    Next
    INDEX
    Explanations

    mathematical and statistical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.88
    TestBed
    -0.66
    hesis
    -0.64
     SEDS
    -0.62
    ieteur
    -0.60
    GEBURTSDATUM
    -0.60
    IGraphics
    -0.60
     referenties
    -0.58
    новништво
    -0.58
     shortly
    -0.57
    POSITIVE LOGITS
    ValueStyle
    0.69
     boyunca
    0.56
     hinweg
    0.55
     mendatang
    0.53
     hinein
    0.52
     سرو
    0.50
    LEGGI
    0.49
     میل
    0.48
    WriteTagHelper
    0.48
    렵
    0.46
    Activations Density 1.358%

    No Known Activations