© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8166
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data formats, such as metadata and properties in a JSON-like structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or identifier-like strings

    np_acts-logits-general · gemini-2.0-flash

    JSON parsing and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EnableWeb
    -0.36
    setupUi
    -0.35
     Braut
    -0.32
     Offisielt
    -0.31
     nerede
    -0.31
    Custom
    -0.31
    af
    -0.30
    ตน
    -0.30
    units
    -0.30
     usah
    -0.29
    POSITIVE LOGITS
     autorytatywna
    0.86
    adaptiveStyles
    0.74
     EconPapers
    0.71
    Personensuche
    0.70
    PostInfinity
    0.60
    tagHelperRunner
    0.59
     ujednoznacz
    0.59
    IVEREF
    0.59
    ScopeManager
    0.58
     CreateTagHelper
    0.57
    Activations Density 0.928%

    No Known Activations