© 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. 24-GEMMASCOPE-RES-16K
    6. 4023
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and syntax, particularly in programming contexts such as initialization of structs and file operations

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

    Code, names, or commands using strings

    np_acts-logits-general · gemini-2.0-flash

    specific items or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malaria
    -0.47
     Hydrogen
    -0.46
     Ethanol
    -0.45
     Arsenic
    -0.45
     Dinosaurs
    -0.45
     Antivirus
    -0.44
     Hypertension
    -0.44
     Obesity
    -0.43
     Flamen
    -0.43
     Helium
    -0.43
    POSITIVE LOGITS
     Place
    1.00
     Line
    0.93
     Point
    0.89
     Spot
    0.88
    Place
    0.87
     Stand
    0.85
     Shot
    0.82
     Room
    0.81
     Set
    0.81
     Pass
    0.81
    Activations Density 1.019%

    No Known Activations