© 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. 13417
    Prev
    Next
    INDEX
    Explanations

    terms related to scanning technologies and processes

    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
     AssemblyCulture
    -0.84
    /**
    -0.81
     CURIAM
    -0.78
     Butterfield
    -0.75
     detalhes
    -0.74
     Wither
    -0.70
     tepung
    -0.69
     Withers
    -0.69
     matières
    -0.69
     detalles
    -0.69
    POSITIVE LOGITS
     scan
    1.48
     Scan
    1.35
    SCAN
    1.28
     SCAN
    1.26
    scan
    1.25
    Scan
    1.24
     scanning
    1.22
     scans
    1.21
    scanning
    1.14
     Scanning
    1.12
    Activations Density 0.157%

    No Known Activations