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-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10758
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving square roots

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

    Square root mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical square roots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.75
    niſſe
    -0.69
     Monfieur
    -0.66
    нгред
    -0.64
     MutableLiveData
    -0.61
     ſeines
    -0.61
    quehanna
    -0.61
     Geiſt
    -0.60
    帖最后由
    -0.60
    
    -0.60
    POSITIVE LOGITS
     OnInit
    0.40
    mailto
    0.32
     getItemId
    0.31
     CreateTagHelper
    0.31
    BeginInit
    0.31
    ️
    0.30
     intptr
    0.29
    ://
    0.28
    stdio
    0.27
    页面存档备份
    0.26
    Activations Density 0.262%

    No Known Activations