© 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. 15-GEMMASCOPE-RES-16K
    11. 2605
    Prev
    Next
    INDEX
    Explanations

    terms related to guidelines and instructions

    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
     Kras
    -0.72
    texttt
    -0.70
    Kras
    -0.64
    forbes
    -0.63
    ServerError
    -0.62
     Vill
    -0.60
     Tennant
    -0.59
    leases
    -0.59
    Morrison
    -0.59
     Marlon
    -0.59
    POSITIVE LOGITS
    Guides
    1.57
     guides
    1.54
     Guides
    1.52
     guide
    1.52
    guide
    1.49
     Guide
    1.48
    Guide
    1.45
     GUIDE
    1.43
     guider
    1.38
    guides
    1.38
    Activations Density 0.089%

    No Known Activations