© 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. 30-GEMMASCOPE-RES-16K
    11. 10685
    Prev
    Next
    INDEX
    Explanations

    phrases related to experimental and analytical processes in scientific contexts

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

    Prepositions following activating tokens

    np_acts-logits-general · gemini-2.0-flash

    applied or used on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.52
    routeProvider
    -0.52
    HostException
    -0.47
    featureID
    -0.47
    UnsafeEnabled
    -0.46
    AccessorTable
    -0.46
    PreferredItem
    -0.44
    MemoryWarning
    -0.44
     EconPapers
    -0.43
    ########.
    -0.43
    POSITIVE LOGITS
     applied
    0.89
     asupra
    0.82
    applied
    0.77
     terhadap
    0.75
     върху
    0.75
    对
    0.70
     onto
    0.65
    對
    0.65
    Applied
    0.63
     aplicado
    0.62
    Activations Density 1.584%

    No Known Activations