© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13373
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures and code execution

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    closing braces and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    
    -1.32
    niſſe
    -1.30
     ujednoznacz
    -1.27
     autorytatywna
    -1.26
    iſchen
    -1.22
    ſicht
    -1.22
    ſchaft
    -1.21
    iſen
    -1.20
    ſſung
    -1.19
    ésultats
    -1.16
    POSITIVE LOGITS
    ↵↵
    0.70
    .
    0.59
    1
    0.54
    2
    0.47
     
    0.46
    ↵
    0.45
    ↵↵↵↵
    0.44
    -
    0.44
    }
    0.41
    0
    0.39
    Activations Density 0.120%

    No Known Activations