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. 16-GEMMASCOPE-RES-16K
    6. 12740
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and adverbs indicating superiority or difference

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

    Comparison: X is [adjective] than Y

    np_acts-logits-general · gemini-2.0-flash

    compares magnitudes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.09
     myſelf
    -1.01
    +#+
    -0.91
    >--}}
    -0.90
    }));
    
    -0.89
     Efq
    -0.89
     дописавши
    -0.88
    ſelves
    -0.86
     تضيفلها
    -0.85
    });*/
    -0.84
    POSITIVE LOGITS
     compared
    1.48
    compared
    1.22
     compare
    1.18
     сравнению
    1.09
     Compared
    1.08
     Compare
    1.07
     dibandingkan
    1.03
    Compared
    1.01
     than
    1.01
    Compare
    0.95
    Activations Density 0.498%

    No Known Activations