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 - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 16063
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "net" in various contexts, particularly in relation to finance or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.90
    SBATCH
    -0.87
     CreateTagHelper
    -0.79
    HasAnnotation
    -0.79
     tartalomajánló
    -0.79
    tipation
    -0.79
    polation
    -0.79
    findpost
    -0.77
     Theſe
    -0.75
    cauc
    -0.74
    POSITIVE LOGITS
     NET
    1.68
     Net
    1.63
     net
    1.60
     nets
    1.52
    Net
    1.51
    NET
    1.46
    net
    1.46
     Nets
    1.39
     netting
    1.18
    nets
    1.16
    Activations Density 0.042%

    No Known Activations