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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 4520
    Prev
    Next
    INDEX
    Explanations

    language tags and properties in code or markup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -1.01
     Monfieur
    -0.98
     оригіналу
    -0.96
     Majefty
    -0.95
    __":
    
    -0.94
     preſent
    -0.94
     pleaſure
    -0.93
    ]';
    -0.93
    ̈́
    -0.93
     neceff
    -0.90
    POSITIVE LOGITS
    lang
    1.96
     Lang
    1.85
     lang
    1.82
    Lang
    1.67
     LANG
    1.45
    LANG
    1.32
    langs
    1.08
     Langley
    1.01
     Langer
    0.80
     Langford
    0.80
    Activations Density 0.048%

    No Known Activations