Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 4587
    Prev
    Next
    INDEX
    Explanations

    code block delimiters, specifically parentheses and curly braces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tril
    -0.52
    isic
    -0.45
    ือก
    -0.43
    Ohne
    -0.43
    наче
    -0.42
    乃至
    -0.42
    ]")]
    -0.41
    ugel
    -0.41
     собой
    -0.41
    >[
    -0.40
    POSITIVE LOGITS
     الحره
    1.08
     للاسماء
    0.85
     propOrder
    0.84
    InputBorder
    0.82
     typelib
    0.81
    CloseOperation
    0.78
     Paglinawan
    0.77
    VersionUID
    0.76
    __':
    
    0.76
    MessageTagHelper
    0.75
    Activations Density 0.017%

    No Known Activations