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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53513
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associated components within programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    вики
    -0.53
     determined
    -0.49
    </blockquote>
    -0.47
    ногие
    -0.45
    ↵↵
    -0.44
     برانيه
    -0.44
    </h4>
    -0.44
    en
    -0.43
     tű
    -0.42
     in
    -0.42
    POSITIVE LOGITS
    Geplaatst
    1.10
     Мексичка
    0.97
     للمعارف
    0.91
    hasOwnProperty
    0.90
    )['
    0.88
     Савезне
    0.87
    цездатний
    0.87
     @"/
    0.82
    +#+#
    0.81
    contentLoaded
    0.80
    Activations Density 0.021%

    No Known Activations