© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2140
    Prev
    Next
    INDEX
    Explanations

    structures related to data types and their definitions in programming contexts

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

    "type" and associated properties

    np_acts-logits-general · gemini-2.0-flash

    key-value type assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.73
    örungen
    -0.70
    sizeCache
    -0.68
    Erreferentziak
    -0.68
     AppBar
    -0.68
     chromatin
    -0.67
     Becken
    -0.66
     Jérusalem
    -0.65
     ISR
    -0.65
     fossa
    -0.64
    POSITIVE LOGITS
     Type
    1.35
     getType
    1.28
     TYPE
    1.27
     types
    1.13
    TYPE
    1.10
     type
    1.08
     Types
    1.07
    Type
    1.06
    types
    1.06
     Ty
    1.03
    Activations Density 0.179%

    No Known Activations