© 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. 18-GEMMASCOPE-RES-16K
    6. 13793
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structure and functionality

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

    Code snippets with file paths

    np_acts-logits-general · gemini-2.0-flash

    code structures and trade-offs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.88
     Houſe
    -0.79
     Jefus
    -0.59
    neſs
    -0.58
     ]
    
    -0.56
     Majefty
    -0.54
     壁纸
    -0.54
    nefs
    -0.53
    BoxLayout
    -0.53
    Normdaten
    -0.53
    POSITIVE LOGITS
     تضيفلها
    0.76
     Audiodateien
    0.75
     الحره
    0.66
    vably
    0.64
     defStyleAttr
    0.64
     consultato
    0.63
    Revenir
    0.62
    ArrowToggle
    0.62
    withOpacity
    0.60
    chtenstein
    0.59
    Activations Density 0.646%

    No Known Activations