© 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. 4797
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and elements related to data structures

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

    Integers and integer-related terms

    np_acts-logits-general · gemini-2.0-flash

    numerical types and values

    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
    
    -0.71
     surla
    -0.62
     noDo
    -0.57
    ⤹
    -0.55
     esternos
    -0.55
     kaarangay
    -0.54
     EconPapers
    -0.54
     @"/
    -0.54
    FieldBuilder
    -0.53
    ConstraintMaker
    -0.52
    POSITIVE LOGITS
     numbers
    1.12
     Numbers
    1.02
    numbers
    0.97
    Numbers
    0.94
     integer
    0.86
     NUMBERS
    0.84
     number
    0.83
    数字
    0.83
     numé
    0.82
     numerical
    0.81
    Activations Density 0.809%

    No Known Activations