© 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. 7636
    Prev
    Next
    INDEX
    Explanations

    references to dates or months

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

    Code or data lists

    np_acts-logits-general · gemini-2.0-flash

    Code structure and punctuation

    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
     bottom
    -0.56
     specifically
    -0.53
    <u>
    -0.53
    <sup>
    -0.52
     specific
    -0.50
    .“
    -0.49
    .​
    -0.49
     overall
    -0.48
     différent
    -0.48
    øren
    -0.48
    POSITIVE LOGITS
     nakalista
    0.77
    ];
    
    0.75
    BeginContext
    0.74
    endphp
    0.69
    \{\\
    0.69
    expandindo
    0.68
    ];
    0.67
    ScopeManager
    0.67
     indisponible
    0.66
     تضيفلها
    0.66
    Activations Density 0.054%

    No Known Activations