Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1751
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
    MLLoader
    -0.63
    RenderAtEndOf
    -0.63
     protoimpl
    -0.59
    XMLSchema
    -0.59
    AutoScale
    -0.57
    Rohy
    -0.57
     Wiktionnaire
    -0.57
     kasarigan
    -0.55
    /**
    -0.54
     ***!
    -0.52
    POSITIVE LOGITS
    期刊论文
    0.29
    PendingIntent
    0.28
     https
    0.27
    AddTagHelper
    0.25
     druk
    0.25
    addWidget
    0.25
    ragalactic
    0.25
    期刊
    0.25
    CrossRef
    0.24
     cheminée
    0.24
    Activations Density 0.472%

    No Known Activations