© 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. 18-GEMMASCOPE-RES-16K
    11. 2136
    Prev
    Next
    INDEX
    Explanations

    code components related to Swift Protobuf implementation and data structures

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

    Code related to dictionaries or maps

    np_acts-logits-general · gemini-2.0-flash

    map dictionary HashMap dict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.74
    AndEndTag
    -0.72
     NgModule
    -0.67
    enterOuterAlt
    -0.63
    InputTagHelper
    -0.63
    DockStyle
    -0.61
    TagMode
    -0.58
    SurfaceView
    -0.57
    fromCharCode
    -0.57
     Administrativna
    -0.56
    POSITIVE LOGITS
     dict
    1.04
    Map
    1.04
     Map
    1.01
     map
    1.00
    dict
    0.99
     Dictionary
    0.99
     dictionary
    0.98
    Dictionary
    0.98
    NSDictionary
    0.94
    Dict
    0.94
    Activations Density 0.410%

    No Known Activations