© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14667
    Prev
    Next
    INDEX
    Explanations

    programming functions and method calls

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

    Code, errors, or locations

    np_acts-logits-general · gemini-2.0-flash

    other things, located in, primarily under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵↵
    -0.81
    enumi
    -0.76
    цездатний
    -0.71
     lenker
    -0.67
     tartalomajánló
    -0.66
    WaitGroup
    -0.65
     disambiguazione
    -0.64
    UIControlState
    -0.64
     Monfieur
    -0.64
    
    -0.62
    POSITIVE LOGITS
     propOrder
    0.56
    PhysRev
    0.50
    RegressionTest
    0.45
    ())),
    0.43
     atra
    0.42
    Myself
    0.42
     Kond
    0.40
     kalangan
    0.40
    codes
    0.40
    mtliche
    0.39
    Activations Density 0.031%

    No Known Activations