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. 21-GEMMASCOPE-RES-16K
    6. 14205
    Prev
    Next
    INDEX
    Explanations

    words related to insurance and insolvency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    柚
    -0.50
    Kaieteur
    -0.48
    DNEY
    -0.48
     suit
    -0.47
     seals
    -0.46
    werben
    -0.45
     Bateman
    -0.45
    CodeAttribute
    -0.44
     dame
    -0.44
    npj
    -0.43
    POSITIVE LOGITS
     Ins
    0.89
    Ins
    0.80
     티즈
    0.79
    AndEndTag
    0.77
     ExecuteAsync
    0.74
     ins
    0.69
     INS
    0.68
     AssemblyProduct
    0.67
     InputDecoration
    0.67
     Inſ
    0.66
    Activations Density 0.087%

    No Known Activations