© 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. 8579
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to labeling and identification

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

    Non-English characters or symbols

    np_acts-logits-general · gemini-2.0-flash

    multi-language programming concepts

    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
     Sociales
    -0.53
     Nacionales
    -0.51
     Agrega
    -0.49
    anskje
    -0.48
     extranjera
    -0.46
     Infór
    -0.45
     Dijo
    -0.43
     propios
    -0.43
     Hadrian
    -0.43
     Añade
    -0.42
    POSITIVE LOGITS
    parsedMessage
    0.63
    tiness
    0.60
    featureID
    0.58
     AssemblyTitle
    0.58
    thansa
    0.56
    cellor
    0.56
     OnInit
    0.55
    édrale
    0.55
     Assignee
    0.55
    rentices
    0.54
    Activations Density 0.019%

    No Known Activations