© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12478
    Prev
    Next
    INDEX
    Explanations

    code structure and programming syntax elements

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

    Code snippets or program-related text

    np_acts-logits-general · gemini-2.0-flash

    code snippets and keywords

    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
    itonitis
    -0.46
     planet
    -0.45
    ConstraintMaker
    -0.45
    fjspx
    -0.43
    pretrained
    -0.42
     Planet
    -0.42
     ursprünglich
    -0.41
    chainId
    -0.41
     Cry
    -0.41
    chir
    -0.41
    POSITIVE LOGITS
    setVerticalGroup
    0.97
    onOptions
    0.48
    
    0.48
    utilisons
    0.47
    EditorGUILayout
    0.42
     updating
    0.42
     transcur
    0.40
    .*")]
    0.40
     update
    0.40
     updates
    0.40
    Activations Density 0.139%

    No Known Activations