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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11110
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the idea of importance or significance, often regardless of various circumstances

    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
     cref
    -0.64
     образом
    -0.58
    ''''
    -0.58
    ]]=
    -0.54
    tiously
    -0.53
    )))));
    -0.50
    exitRule
    -0.48
     wiederum
    -0.48
    Пу
    -0.47
     الفلسطينية
    -0.47
    POSITIVE LOGITS
    regardless
    1.41
     Regardless
    1.40
     regardless
    1.38
    Regardless
    1.36
    dientemente
    1.20
     irrespective
    1.19
    不论
    1.00
    AddTagHelper
    1.00
    hichever
    0.99
     apapun
    0.93
    Activations Density 0.110%

    No Known Activations