© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 465
    Prev
    Next
    INDEX
    Explanations

    syntax and function calls in programming code

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

    code-related syntax and structures

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

    . ) ] # $$ men

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mix
    -0.82
     confusion
    -0.80
     mix
    -0.79
    Mix
    -0.74
     MIX
    -0.72
     conf
    -0.71
     mixes
    -0.69
     Mixtures
    -0.69
    mix
    -0.68
     Confusion
    -0.66
    POSITIVE LOGITS
    shape
    0.82
     shape
    0.79
    sum
    0.70
     shapes
    0.66
    XMLSchema
    0.66
     sum
    0.60
     StatefulWidget
    0.60
    LookAnd
    0.60
    SHAPE
    0.60
     transfieras
    0.59
    Activations Density 0.039%

    No Known Activations